Halaman ini diterjemahkan oleh Cloud Translation API.
Switch to English

Pengelompokan berat dalam contoh Keras

Lihat di TensorFlow.org Jalankan di Google Colab Lihat sumber di GitHub Unduh buku catatan

Gambaran

Selamat datang di contoh ujung ke ujung untuk pengelompokan berat badan , bagian dari TensorFlow Model Optimization Toolkit.

Halaman lain

Untuk pengantar tentang pengelompokan berat badan dan untuk menentukan apakah Anda harus menggunakannya (termasuk apa yang didukung), lihat halaman ikhtisar .

Untuk menemukan API yang Anda butuhkan dengan cepat untuk kasus penggunaan Anda (di luar pengelompokan model sepenuhnya dengan 16 kluster), lihat panduan komprehensif .

Isi

Dalam tutorial, Anda akan:

  1. Latih model tf.keras untuk dataset MNIST dari awal.
  2. Sempurnakan model dengan menerapkan API pengelompokan berat dan lihat akurasinya.
  3. Buat model TF dan TFLite 6x lebih kecil dari pengelompokan.
  4. Buat model TFLite 8x lebih kecil dari menggabungkan pengelompokan berat badan dan kuantisasi pasca-pelatihan.
  5. Lihat ketepatan ketelitian dari TF ke TFLite.

Mempersiapkan

Anda dapat menjalankan Jupyter Notebook ini di virtualenv atau colab lokal Anda. Untuk detail pengaturan dependensi, silakan merujuk ke panduan instalasi .

 pip install -q tensorflow-model-optimization
 import tensorflow as tf
from tensorflow import keras

import numpy as np
import tempfile
import zipfile
import os
 

Latih model tf.keras untuk MNIST tanpa pengelompokan

 # Load MNIST dataset
mnist = keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

# Normalize the input image so that each pixel value is between 0 to 1.
train_images = train_images / 255.0
test_images  = test_images / 255.0

# Define the model architecture.
model = keras.Sequential([
    keras.layers.InputLayer(input_shape=(28, 28)),
    keras.layers.Reshape(target_shape=(28, 28, 1)),
    keras.layers.Conv2D(filters=12, kernel_size=(3, 3), activation=tf.nn.relu),
    keras.layers.MaxPooling2D(pool_size=(2, 2)),
    keras.layers.Flatten(),
    keras.layers.Dense(10)
])

# Train the digit classification model
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

model.fit(
    train_images,
    train_labels,
    validation_split=0.1,
    epochs=10
)
 
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz
11493376/11490434 [==============================] - 0s 0us/step
Epoch 1/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.3352 - accuracy: 0.9039 - val_loss: 0.1543 - val_accuracy: 0.9575
Epoch 2/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.1535 - accuracy: 0.9559 - val_loss: 0.0948 - val_accuracy: 0.9745
Epoch 3/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.1003 - accuracy: 0.9715 - val_loss: 0.0750 - val_accuracy: 0.9788
Epoch 4/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.0791 - accuracy: 0.9768 - val_loss: 0.0652 - val_accuracy: 0.9828
Epoch 5/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.0669 - accuracy: 0.9803 - val_loss: 0.0663 - val_accuracy: 0.9807
Epoch 6/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.0589 - accuracy: 0.9820 - val_loss: 0.0581 - val_accuracy: 0.9833
Epoch 7/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.0528 - accuracy: 0.9840 - val_loss: 0.0584 - val_accuracy: 0.9832
Epoch 8/10
1688/1688 [==============================] - 8s 5ms/step - loss: 0.0479 - accuracy: 0.9854 - val_loss: 0.0560 - val_accuracy: 0.9838
Epoch 9/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.0434 - accuracy: 0.9867 - val_loss: 0.0550 - val_accuracy: 0.9853
Epoch 10/10
1688/1688 [==============================] - 7s 4ms/step - loss: 0.0393 - accuracy: 0.9880 - val_loss: 0.0571 - val_accuracy: 0.9845

<tensorflow.python.keras.callbacks.History at 0x7fd1a1e18668>

Evaluasi model baseline dan simpan untuk penggunaan nanti

 _, baseline_model_accuracy = model.evaluate(
    test_images, test_labels, verbose=0)

print('Baseline test accuracy:', baseline_model_accuracy)

_, keras_file = tempfile.mkstemp('.h5')
print('Saving model to: ', keras_file)
tf.keras.models.save_model(model, keras_file, include_optimizer=False)
 
Baseline test accuracy: 0.9805999994277954
Saving model to:  /tmp/tmpphs68ctq.h5

Sempurnakan model pra-terlatih dengan pengelompokan

Terapkan API cluster_weights() ke seluruh model yang sudah dilatih untuk menunjukkan efektivitasnya dalam mengurangi ukuran model setelah menerapkan zip sambil tetap menjaga akurasi yang layak. Untuk cara terbaik menyeimbangkan akurasi dan tingkat kompresi untuk kasus penggunaan Anda, lihat contoh per lapisan dalam panduan komprehensif .

Tentukan model dan terapkan API pengelompokan

Sebelum Anda meneruskan model ke API pengelompokan, pastikan itu dilatih dan menunjukkan keakuratan yang dapat diterima.

 import tensorflow_model_optimization as tfmot

cluster_weights = tfmot.clustering.keras.cluster_weights
CentroidInitialization = tfmot.clustering.keras.CentroidInitialization

clustering_params = {
  'number_of_clusters': 16,
  'cluster_centroids_init': CentroidInitialization.LINEAR
}

# Cluster a whole model
clustered_model = cluster_weights(model, **clustering_params)

# Use smaller learning rate for fine-tuning clustered model
opt = tf.keras.optimizers.Adam(learning_rate=1e-5)

clustered_model.compile(
  loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
  optimizer=opt,
  metrics=['accuracy'])

clustered_model.summary()
 
Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
cluster_reshape (ClusterWeig (None, 28, 28, 1)         0         
_________________________________________________________________
cluster_conv2d (ClusterWeigh (None, 26, 26, 12)        136       
_________________________________________________________________
cluster_max_pooling2d (Clust (None, 13, 13, 12)        0         
_________________________________________________________________
cluster_flatten (ClusterWeig (None, 2028)              0         
_________________________________________________________________
cluster_dense (ClusterWeight (None, 10)                20306     
=================================================================
Total params: 20,442
Trainable params: 54
Non-trainable params: 20,388
_________________________________________________________________

Sempurnakan model dan evaluasi akurasi terhadap baseline

Sempurnakan model dengan pengelompokan selama 1 zaman.

 # Fine-tune model
clustered_model.fit(
  train_images,
  train_labels,
  batch_size=500,
  epochs=1,
  validation_split=0.1)
 
108/108 [==============================] - 2s 16ms/step - loss: 0.0535 - accuracy: 0.9821 - val_loss: 0.0692 - val_accuracy: 0.9803

<tensorflow.python.keras.callbacks.History at 0x7fd18437ee10>

Untuk contoh ini, ada kehilangan minimal dalam akurasi tes setelah pengelompokan, dibandingkan dengan baseline.

 _, clustered_model_accuracy = clustered_model.evaluate(
  test_images, test_labels, verbose=0)

print('Baseline test accuracy:', baseline_model_accuracy)
print('Clustered test accuracy:', clustered_model_accuracy)
 
Baseline test accuracy: 0.9805999994277954
Clustered test accuracy: 0.9753000140190125

Buat 6x model yang lebih kecil dari pengelompokan

strip_clustering dan penerapan algoritma kompresi standar (misalnya via gzip) diperlukan untuk melihat manfaat kompresi dari clustering.

Pertama, buat model kompresibel untuk TensorFlow. Di sini, strip_clustering menghapus semua variabel (mis. tf.Variable untuk menyimpan cluster centroid dan indeks) yang hanya perlu dikelompokkan selama pelatihan, yang jika tidak akan menambah ukuran model selama inferensi.

 final_model = tfmot.clustering.keras.strip_clustering(clustered_model)

_, clustered_keras_file = tempfile.mkstemp('.h5')
print('Saving clustered model to: ', clustered_keras_file)
tf.keras.models.save_model(final_model, clustered_keras_file, 
                           include_optimizer=False)
 
Saving clustered model to:  /tmp/tmpfnmtfvf8.h5

Kemudian, buat model kompresibel untuk TFLite. Anda bisa mengonversi model kluster ke format yang dapat dijalankan di backend yang Anda targetkan. TensorFlow Lite adalah contoh yang dapat Anda gunakan untuk menggunakan perangkat seluler.

 clustered_tflite_file = '/tmp/clustered_mnist.tflite'
converter = tf.lite.TFLiteConverter.from_keras_model(final_model)
tflite_clustered_model = converter.convert()
with open(clustered_tflite_file, 'wb') as f:
  f.write(tflite_clustered_model)
print('Saved clustered TFLite model to:', clustered_tflite_file)
 
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/training/tracking/tracking.py:111: Model.state_updates (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.
Instructions for updating:
This property should not be used in TensorFlow 2.0, as updates are applied automatically.
WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.6/site-packages/tensorflow/python/training/tracking/tracking.py:111: Layer.updates (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
This property should not be used in TensorFlow 2.0, as updates are applied automatically.
INFO:tensorflow:Assets written to: /tmp/tmpe966h_56/assets
Saved clustered TFLite model to: /tmp/clustered_mnist.tflite

Tentukan fungsi pembantu untuk benar-benar memampatkan model melalui gzip dan mengukur ukuran zip.

 def get_gzipped_model_size(file):
  # It returns the size of the gzipped model in bytes.
  import os
  import zipfile

  _, zipped_file = tempfile.mkstemp('.zip')
  with zipfile.ZipFile(zipped_file, 'w', compression=zipfile.ZIP_DEFLATED) as f:
    f.write(file)

  return os.path.getsize(zipped_file)
 

Bandingkan dan lihat bahwa model 6x lebih kecil dari pengelompokan

 print("Size of gzipped baseline Keras model: %.2f bytes" % (get_gzipped_model_size(keras_file)))
print("Size of gzipped clustered Keras model: %.2f bytes" % (get_gzipped_model_size(clustered_keras_file)))
print("Size of gzipped clustered TFlite model: %.2f bytes" % (get_gzipped_model_size(clustered_tflite_file)))
 
Size of gzipped baseline Keras model: 78076.00 bytes
Size of gzipped clustered Keras model: 13362.00 bytes
Size of gzipped clustered TFlite model: 12982.00 bytes

Buat model TFLite 8x lebih kecil dari menggabungkan pengelompokan berat badan dan kuantisasi pasca-pelatihan

Anda dapat menerapkan kuantisasi pasca-pelatihan untuk model berkerumun untuk manfaat tambahan.

 converter = tf.lite.TFLiteConverter.from_keras_model(final_model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
tflite_quant_model = converter.convert()

_, quantized_and_clustered_tflite_file = tempfile.mkstemp('.tflite')

with open(quantized_and_clustered_tflite_file, 'wb') as f:
  f.write(tflite_quant_model)

print('Saved quantized and clustered TFLite model to:', quantized_and_clustered_tflite_file)
print("Size of gzipped baseline Keras model: %.2f bytes" % (get_gzipped_model_size(keras_file)))
print("Size of gzipped clustered and quantized TFlite model: %.2f bytes" % (get_gzipped_model_size(quantized_and_clustered_tflite_file)))
 
INFO:tensorflow:Assets written to: /tmp/tmpg0gw8r5x/assets

INFO:tensorflow:Assets written to: /tmp/tmpg0gw8r5x/assets

Saved quantized and clustered TFLite model to: /tmp/tmp43crqft1.tflite
Size of gzipped baseline Keras model: 78076.00 bytes
Size of gzipped clustered and quantized TFlite model: 9830.00 bytes

Lihat ketepatan ketelitian dari TF ke TFLite

Tetapkan fungsi pembantu untuk mengevaluasi model TFLite pada dataset uji.

 def eval_model(interpreter):
  input_index = interpreter.get_input_details()[0]["index"]
  output_index = interpreter.get_output_details()[0]["index"]

  # Run predictions on every image in the "test" dataset.
  prediction_digits = []
  for i, test_image in enumerate(test_images):
    if i % 1000 == 0:
      print('Evaluated on {n} results so far.'.format(n=i))
    # Pre-processing: add batch dimension and convert to float32 to match with
    # the model's input data format.
    test_image = np.expand_dims(test_image, axis=0).astype(np.float32)
    interpreter.set_tensor(input_index, test_image)

    # Run inference.
    interpreter.invoke()

    # Post-processing: remove batch dimension and find the digit with highest
    # probability.
    output = interpreter.tensor(output_index)
    digit = np.argmax(output()[0])
    prediction_digits.append(digit)

  print('\n')
  # Compare prediction results with ground truth labels to calculate accuracy.
  prediction_digits = np.array(prediction_digits)
  accuracy = (prediction_digits == test_labels).mean()
  return accuracy
 

Anda mengevaluasi model, yang telah dikelompokkan dan dikuantisasi, dan kemudian melihat akurasi dari TensorFlow berlanjut ke backend TFLite.

 interpreter = tf.lite.Interpreter(model_content=tflite_quant_model)
interpreter.allocate_tensors()

test_accuracy = eval_model(interpreter)

print('Clustered and quantized TFLite test_accuracy:', test_accuracy)
print('Clustered TF test accuracy:', clustered_model_accuracy)
 
Evaluated on 0 results so far.
Evaluated on 1000 results so far.
Evaluated on 2000 results so far.
Evaluated on 3000 results so far.
Evaluated on 4000 results so far.
Evaluated on 5000 results so far.
Evaluated on 6000 results so far.
Evaluated on 7000 results so far.
Evaluated on 8000 results so far.
Evaluated on 9000 results so far.


Clustered and quantized TFLite test_accuracy: 0.975
Clustered TF test accuracy: 0.9753000140190125

Kesimpulan

Dalam tutorial ini, Anda melihat cara membuat model yang dikelompokkan dengan TensorFlow Model Optimization Toolkit API. Lebih khusus lagi, Anda telah melalui contoh ujung ke ujung untuk membuat model 8x lebih kecil untuk MNIST dengan perbedaan akurasi minimal. Kami mendorong Anda untuk mencoba kemampuan baru ini, yang dapat menjadi sangat penting untuk penempatan di lingkungan yang terbatas sumber daya.