Se usó la API de Cloud Translation para traducir esta página.
Switch to English

Regularización adversaria para clasificación de imágenes

Ver en TensorFlow.org Ejecutar en Google Colab Ver fuente en GitHub

Visión general

En este tutorial, exploraremos el uso del aprendizaje adversario ( Goodfellow et al., 2014 ) para la clasificación de imágenes utilizando el marco de aprendizaje estructurado neuronal (NSL).

La idea central del aprendizaje adversario es entrenar un modelo con datos perturbados por el adversario (llamados ejemplos adversarios) además de los datos de entrenamiento orgánico. Para el ojo humano, estos ejemplos contradictorios tienen el mismo aspecto que el original, pero la purtubación hará que el modelo se confunda y haga predicciones o clasificaciones incorrectas. Los ejemplos contradictorios se construyen para engañar intencionalmente al modelo para que haga predicciones o clasificaciones incorrectas. Al entrenar con tales ejemplos, el modelo aprende a ser robusto frente a las perturbaciones adversas al hacer predicciones.

En este tutorial, ilustramos el siguiente procedimiento de aplicación del aprendizaje contradictorio para obtener modelos robustos utilizando el marco de aprendizaje estructurado neuronal:

  1. Cree una red neuronal como modelo base. En este tutorial, el modelo base se crea con la API funcional tf.keras ; este procedimiento es compatible con modelos creados por tf.keras API secuenciales y de subclases también. Para obtener más información sobre los modelos de Keras en TensorFlow, consulte esta documentación .
  2. Envuelva el modelo base con la clase contenedora AdversarialRegularization , que es proporcionada por el marco NSL, para crear una nueva instancia tf.keras.Model . Este nuevo modelo incluirá la pérdida adversaria como término de regularización en su objetivo formativo.
  3. Convierta ejemplos de los datos de entrenamiento en diccionarios de funciones.
  4. Capacitar y evaluar el nuevo modelo.

Preparar

Instale el paquete Neural Structured Learning.

pip install --quiet neural-structured-learning
WARNING: You are using pip version 20.2.2; however, version 20.2.3 is available.
You should consider upgrading via the '/tmpfs/src/tf_docs_env/bin/python -m pip install --upgrade pip' command.

Importar bibliotecas. neural_structured_learning a nsl .

import matplotlib.pyplot as plt
import neural_structured_learning as nsl
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds

Hiperparámetros

Recopilamos y explicamos los hiperparámetros (en un objeto HParams ) para el entrenamiento y la evaluación del modelo.

De entrada y salida:

  • input_shape : La forma del tensor de entrada. Cada imagen tiene 28 por 28 píxeles con 1 canal.
  • num_classes : Hay un total de 10 clases, correspondientes a 10 dígitos [0-9].

Arquitectura modelo:

  • conv_filters : una lista de números, cada uno de los cuales especifica el número de filtros en una capa convolucional.
  • kernel_size : El tamaño de la ventana de convolución 2D, compartido por todas las capas convolucionales.
  • pool_size : factores para reducir la escala de la imagen en cada capa de agrupación máxima.
  • num_fc_units : El número de unidades (es decir, ancho) de cada capa completamente conectada.

Capacitación y evaluación:

  • batch_size : tamaño de lote usado para entrenamiento y evaluación.
  • epochs : el número de épocas de entrenamiento.

Aprendizaje adversario:

  • adv_multiplier : el peso de la pérdida adversaria en el objetivo de entrenamiento, en relación con la pérdida etiquetada.
  • adv_step_size : la magnitud de la perturbación adversaria.
  • adv_grad_norm : La norma para medir la magnitud de la perturbación adversaria.
class HParams(object):
  def __init__(self):
    self.input_shape = [28, 28, 1]
    self.num_classes = 10
    self.conv_filters = [32, 64, 64]
    self.kernel_size = (3, 3)
    self.pool_size = (2, 2)
    self.num_fc_units = [64]
    self.batch_size = 32
    self.epochs = 5
    self.adv_multiplier = 0.2
    self.adv_step_size = 0.2
    self.adv_grad_norm = 'infinity'

HPARAMS = HParams()

Conjunto de datos MNIST

El conjunto de datos MNIST contiene imágenes en escala de grises de dígitos escritos a mano (de '0' a '9'). Cada imagen muestra un dígito a baja resolución (28 por 28 píxeles). La tarea involucrada es clasificar las imágenes en 10 categorías, una por dígito.

Aquí cargamos el conjunto de datos MNIST de TensorFlow Datasets . Maneja la descarga de datos y la construcción de un tf.data.Dataset . El conjunto de datos cargado tiene dos subconjuntos:

  • train con 60.000 ejemplos, y
  • test con 10,000 ejemplos.

Los ejemplos de ambos subconjuntos se almacenan en diccionarios de funciones con las dos claves siguientes:

  • image : matriz de valores de píxeles, que van de 0 a 255.
  • label : label Groundtruth, que va de 0 a 9.
datasets = tfds.load('mnist')

train_dataset = datasets['train']
test_dataset = datasets['test']

IMAGE_INPUT_NAME = 'image'
LABEL_INPUT_NAME = 'label'
WARNING:absl:Dataset mnist is hosted on GCS. It will automatically be downloaded to your
local data directory. If you'd instead prefer to read directly from our public
GCS bucket (recommended if you're running on GCP), you can instead pass
`try_gcs=True` to `tfds.load` or set `data_dir=gs://tfds-data/datasets`.


Downloading and preparing dataset mnist/3.0.1 (download: 11.06 MiB, generated: 21.00 MiB, total: 32.06 MiB) to /home/kbuilder/tensorflow_datasets/mnist/3.0.1...
Dataset mnist downloaded and prepared to /home/kbuilder/tensorflow_datasets/mnist/3.0.1. Subsequent calls will reuse this data.

Para que el modelo sea numéricamente estable, normalizamos los valores de píxeles a [0, 1] mapeando el conjunto de datos sobre la función de normalize . Después de mezclar el conjunto de entrenamiento y el procesamiento por lotes, convertimos los ejemplos en tuplas de características (image, label) para entrenar el modelo base. También proporcionamos una función para convertir de tuplas a diccionarios para su uso posterior.

def normalize(features):
  features[IMAGE_INPUT_NAME] = tf.cast(
      features[IMAGE_INPUT_NAME], dtype=tf.float32) / 255.0
  return features

def convert_to_tuples(features):
  return features[IMAGE_INPUT_NAME], features[LABEL_INPUT_NAME]

def convert_to_dictionaries(image, label):
  return {IMAGE_INPUT_NAME: image, LABEL_INPUT_NAME: label}

train_dataset = train_dataset.map(normalize).shuffle(10000).batch(HPARAMS.batch_size).map(convert_to_tuples)
test_dataset = test_dataset.map(normalize).batch(HPARAMS.batch_size).map(convert_to_tuples)

Modelo base

Nuestro modelo base será una red neuronal que consta de 3 capas convolucionales seguidas de 2 capas completamente conectadas (como se define en HPARAMS ). Aquí lo definimos utilizando la API funcional de Keras. No dude en probar otras API o arquitecturas de modelos.

def build_base_model(hparams):
  """Builds a model according to the architecture defined in `hparams`."""
  inputs = tf.keras.Input(
      shape=hparams.input_shape, dtype=tf.float32, name=IMAGE_INPUT_NAME)

  x = inputs
  for i, num_filters in enumerate(hparams.conv_filters):
    x = tf.keras.layers.Conv2D(
        num_filters, hparams.kernel_size, activation='relu')(
            x)
    if i < len(hparams.conv_filters) - 1:
      # max pooling between convolutional layers
      x = tf.keras.layers.MaxPooling2D(hparams.pool_size)(x)
  x = tf.keras.layers.Flatten()(x)
  for num_units in hparams.num_fc_units:
    x = tf.keras.layers.Dense(num_units, activation='relu')(x)
  pred = tf.keras.layers.Dense(hparams.num_classes, activation='softmax')(x)
  model = tf.keras.Model(inputs=inputs, outputs=pred)
  return model
base_model = build_base_model(HPARAMS)
base_model.summary()
Model: "functional_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
image (InputLayer)           [(None, 28, 28, 1)]       0         
_________________________________________________________________
conv2d (Conv2D)              (None, 26, 26, 32)        320       
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 13, 13, 32)        0         
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 11, 11, 64)        18496     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 5, 5, 64)          0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 3, 3, 64)          36928     
_________________________________________________________________
flatten (Flatten)            (None, 576)               0         
_________________________________________________________________
dense (Dense)                (None, 64)                36928     
_________________________________________________________________
dense_1 (Dense)              (None, 10)                650       
=================================================================
Total params: 93,322
Trainable params: 93,322
Non-trainable params: 0
_________________________________________________________________

A continuación, entrenamos y evaluamos el modelo base.

base_model.compile(optimizer='adam', loss='sparse_categorical_crossentropy',
                   metrics=['acc'])
base_model.fit(train_dataset, epochs=HPARAMS.epochs)
Epoch 1/5
1875/1875 [==============================] - 15s 8ms/step - loss: 0.1527 - acc: 0.9531
Epoch 2/5
1875/1875 [==============================] - 14s 8ms/step - loss: 0.0493 - acc: 0.9849
Epoch 3/5
1875/1875 [==============================] - 14s 8ms/step - loss: 0.0352 - acc: 0.9893
Epoch 4/5
1875/1875 [==============================] - 14s 8ms/step - loss: 0.0276 - acc: 0.9916
Epoch 5/5
1875/1875 [==============================] - 14s 8ms/step - loss: 0.0220 - acc: 0.9930

<tensorflow.python.keras.callbacks.History at 0x7fb5942bde80>
results = base_model.evaluate(test_dataset)
named_results = dict(zip(base_model.metrics_names, results))
print('\naccuracy:', named_results['acc'])
313/313 [==============================] - 1s 3ms/step - loss: 0.0383 - acc: 0.9887

accuracy: 0.9886999726295471

Podemos ver que el modelo base alcanza un 99% de precisión en el equipo de prueba. Veremos qué tan robusto es en Robustez bajo perturbaciones adversas a continuación.

Modelo adversario-regularizado

Aquí mostramos cómo incorporar el entrenamiento contradictorio en un modelo de Keras con unas pocas líneas de código, utilizando el marco NSL. El modelo base se envuelve para crear un nuevo tf.Keras.Model , cuyo objetivo de entrenamiento incluye la regularización adversaria.

Primero, creamos un objeto de configuración con todos los hiperparámetros relevantes usando la función auxiliar nsl.configs.make_adv_reg_config .

adv_config = nsl.configs.make_adv_reg_config(
    multiplier=HPARAMS.adv_multiplier,
    adv_step_size=HPARAMS.adv_step_size,
    adv_grad_norm=HPARAMS.adv_grad_norm
)

Ahora podemos envolver un modelo base con AdversarialRegularization . Aquí creamos un nuevo modelo base ( base_adv_model ), de modo que el existente ( base_model ) pueda usarse en una comparación posterior.

El adv_model devuelto es un objeto tf.keras.Model , cuyo objetivo de entrenamiento incluye un término de regularización para la pérdida adversaria. Para calcular esa pérdida, el modelo debe tener acceso a la información de la etiqueta ( label característica), además de la entrada regular ( image característica). Por esta razón, convertimos los ejemplos en los conjuntos de datos de tuplas a diccionarios. Y le decimos al modelo qué característica contiene la información de la etiqueta a través del parámetro label_keys .

base_adv_model = build_base_model(HPARAMS)
adv_model = nsl.keras.AdversarialRegularization(
    base_adv_model,
    label_keys=[LABEL_INPUT_NAME],
    adv_config=adv_config
)

train_set_for_adv_model = train_dataset.map(convert_to_dictionaries)
test_set_for_adv_model = test_dataset.map(convert_to_dictionaries)

A continuación, compilamos, entrenamos y evaluamos el modelo adversarial-regularized. Puede haber advertencias como "Falta la salida del diccionario de pérdidas", lo cual está bien porque adv_model no se basa en la implementación base para calcular la pérdida total.

adv_model.compile(optimizer='adam', loss='sparse_categorical_crossentropy',
                   metrics=['acc'])
adv_model.fit(train_set_for_adv_model, epochs=HPARAMS.epochs)
Epoch 1/5
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:AutoGraph could not transform <bound method Socket.send of <zmq.sugar.socket.Socket object at 0x7fb63bbbb0b0>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: <cyfunction Socket.send at 0x7fb6386d35c0> is not a module, class, method, function, traceback, frame, or code object
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert

Warning:absl:Cannot perturb features dict_keys(['label'])WARNING:tensorflow:AutoGraph could not transform <bound method Socket.send of <zmq.sugar.socket.Socket object at 0x7fb63bbbb0b0>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: <cyfunction Socket.send at 0x7fb6386d35c0> is not a module, class, method, function, traceback, frame, or code object
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert

Warning: AutoGraph could not transform <bound method Socket.send of <zmq.sugar.socket.Socket object at 0x7fb63bbbb0b0>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, `export AUTOGRAPH_VERBOSITY=10`) and attach the full output.
Cause: <cyfunction Socket.send at 0x7fb6386d35c0> is not a module, class, method, function, traceback, frame, or code object
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert



Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

1875/1875 [==============================] - 25s 13ms/step - loss: 0.2922 - sparse_categorical_crossentropy: 0.1379 - sparse_categorical_accuracy: 0.9571 - scaled_adversarial_loss: 0.1543
Epoch 2/5
1875/1875 [==============================] - 25s 13ms/step - loss: 0.1213 - sparse_categorical_crossentropy: 0.0397 - sparse_categorical_accuracy: 0.9875 - scaled_adversarial_loss: 0.0816
Epoch 3/5
1875/1875 [==============================] - 26s 14ms/step - loss: 0.0910 - sparse_categorical_crossentropy: 0.0287 - sparse_categorical_accuracy: 0.9908 - scaled_adversarial_loss: 0.0623
Epoch 4/5
1875/1875 [==============================] - 25s 13ms/step - loss: 0.0715 - sparse_categorical_crossentropy: 0.0211 - sparse_categorical_accuracy: 0.9933 - scaled_adversarial_loss: 0.0504
Epoch 5/5
1875/1875 [==============================] - 25s 13ms/step - loss: 0.0598 - sparse_categorical_crossentropy: 0.0167 - sparse_categorical_accuracy: 0.9949 - scaled_adversarial_loss: 0.0432

<tensorflow.python.keras.callbacks.History at 0x7fb56c2f2d68>
results = adv_model.evaluate(test_set_for_adv_model)
named_results = dict(zip(adv_model.metrics_names, results))
print('\naccuracy:', named_results['sparse_categorical_accuracy'])
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

313/313 [==============================] - 2s 7ms/step - loss: 0.0673 - sparse_categorical_crossentropy: 0.0239 - sparse_categorical_accuracy: 0.9924 - scaled_adversarial_loss: 0.0434

accuracy: 0.9923999905586243

Podemos ver que el modelo adversarial-regularized también funciona muy bien (99% de precisión) en el conjunto de prueba.

Robustez ante perturbaciones adversas

Ahora comparamos el modelo base y el modelo adversarial-regularizado en cuanto a robustez bajo perturbación adversaria.

Usaremos la función AdversarialRegularization.perturb_on_batch para generar ejemplos perturbados por el adversario. Y nos gustaría la generación basada en el modelo base. Para hacerlo, envolvemos el modelo base con AdversarialRegularization . Tenga en cuenta que mientras no Model.fit entrenamiento ( Model.fit ), las variables aprendidas en el modelo no cambiarán y el modelo seguirá siendo el mismo que en la sección Modelo base .

reference_model = nsl.keras.AdversarialRegularization(
    base_model,
    label_keys=[LABEL_INPUT_NAME],
    adv_config=adv_config)
reference_model.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['acc'])

Recopilamos en un diccionario los modelos a evaluar, y también creamos un objeto métrico para cada uno de los modelos.

Tenga en cuenta que tomamos adv_model.base_model para tener el mismo formato de entrada (sin requerir información de etiqueta) que el modelo base. Las variables aprendidas en adv_model.base_model son las mismas que las de adv_model .

models_to_eval = {
    'base': base_model,
    'adv-regularized': adv_model.base_model
}
metrics = {
    name: tf.keras.metrics.SparseCategoricalAccuracy()
    for name in models_to_eval.keys()
}

Aquí está el ciclo para generar ejemplos perturbados y evaluar modelos con ellos. Guardamos las imágenes perturbadas, las etiquetas y las predicciones para su visualización en la siguiente sección.

perturbed_images, labels, predictions = [], [], []

for batch in test_set_for_adv_model:
  perturbed_batch = reference_model.perturb_on_batch(batch)
  # Clipping makes perturbed examples have the same range as regular ones.
  perturbed_batch[IMAGE_INPUT_NAME] = tf.clip_by_value(                          
      perturbed_batch[IMAGE_INPUT_NAME], 0.0, 1.0)
  y_true = perturbed_batch.pop(LABEL_INPUT_NAME)
  perturbed_images.append(perturbed_batch[IMAGE_INPUT_NAME].numpy())
  labels.append(y_true.numpy())
  predictions.append({})
  for name, model in models_to_eval.items():
    y_pred = model(perturbed_batch)
    metrics[name](y_true, y_pred)
    predictions[-1][name] = tf.argmax(y_pred, axis=-1).numpy()

for name, metric in metrics.items():
  print('%s model accuracy: %f' % (name, metric.result().numpy()))
WARNING:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64
WARNING:absl:Cannot perturb features dict_keys(['label'])

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the watched tensor must be floating (e.g. tf.float32), got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

Warning:tensorflow:The dtype of the source tensor must be floating (e.g. tf.float32) when calling GradientTape.gradient, got tf.int64

base model accuracy: 0.586400
adv-regularized model accuracy: 0.962400

Podemos ver que la precisión del modelo base cae drásticamente (de 99% a aproximadamente 50%) cuando la entrada se perturba de manera adversa. Por otro lado, la precisión del modelo adversario-regularizado solo se degrada un poco (del 99% al 95%). Esto demuestra la eficacia del aprendizaje contradictorio para mejorar la solidez del modelo.

Ejemplos de imágenes perturbadas por el adversario

Aquí echamos un vistazo a las imágenes perturbadas por el adversario. Podemos ver que las imágenes perturbadas todavía muestran dígitos reconocibles por humanos, pero pueden engañar con éxito al modelo base.

batch_index = 0

batch_image = perturbed_images[batch_index]
batch_label = labels[batch_index]
batch_pred = predictions[batch_index]

batch_size = HPARAMS.batch_size
n_col = 4
n_row = (batch_size + n_col - 1) / n_col

print('accuracy in batch %d:' % batch_index)
for name, pred in batch_pred.items():
  print('%s model: %d / %d' % (name, np.sum(batch_label == pred), batch_size))

plt.figure(figsize=(15, 15))
for i, (image, y) in enumerate(zip(batch_image, batch_label)):
  y_base = batch_pred['base'][i]
  y_adv = batch_pred['adv-regularized'][i]
  plt.subplot(n_row, n_col, i+1)
  plt.title('true: %d, base: %d, adv: %d' % (y, y_base, y_adv))
  plt.imshow(tf.keras.preprocessing.image.array_to_img(image), cmap='gray')
  plt.axis('off')

plt.show()
accuracy in batch 0:
base model: 17 / 32
adv-regularized model: 31 / 32

png

Conclusión

Hemos demostrado el uso del aprendizaje adversario para la clasificación de imágenes utilizando el marco de aprendizaje estructurado neuronal (NSL). Alentamos a los usuarios a experimentar con diferentes configuraciones adversas (en hiperparámetros) y ver cómo afectan la solidez del modelo.