View on TensorFlow.org | Run in Google Colab | View source on GitHub | Download notebook |

## Overview

Welcome to an end-to-end example for magnitude-based *weight pruning*.

### Other pages

For an introduction to what pruning is and to determine if you should use it (including what's supported), see the overview page.

To quickly find the APIs you need for your use case (beyond fully pruning a model with 80% sparsity), see the comprehensive guide.

### Summary

In this tutorial, you will:

- Train a
`tf.keras`

model for MNIST from scratch. - Fine tune the model by applying the pruning API and see the accuracy.
- Create 3x smaller TF and TFLite models from pruning.
- Create a 10x smaller TFLite model from combining pruning and post-training quantization.
- See the persistence of accuracy from TF to TFLite.

## Setup

` pip install -q tensorflow-model-optimization`

```
import tempfile
import os
import tensorflow as tf
import numpy as np
from tensorflow import keras
%load_ext tensorboard
```

## Train a model for MNIST without pruning

```
# 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 and 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='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,
epochs=4,
validation_split=0.1,
)
```

Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz 11493376/11490434 [==============================] - 0s 0us/step Epoch 1/4 1688/1688 [==============================] - 10s 6ms/step - loss: 0.2785 - accuracy: 0.9220 - val_loss: 0.1031 - val_accuracy: 0.9740 Epoch 2/4 1688/1688 [==============================] - 9s 5ms/step - loss: 0.1063 - accuracy: 0.9691 - val_loss: 0.0782 - val_accuracy: 0.9790 Epoch 3/4 1688/1688 [==============================] - 9s 5ms/step - loss: 0.0815 - accuracy: 0.9765 - val_loss: 0.0788 - val_accuracy: 0.9775 Epoch 4/4 1688/1688 [==============================] - 9s 5ms/step - loss: 0.0689 - accuracy: 0.9797 - val_loss: 0.0633 - val_accuracy: 0.9840 <tensorflow.python.keras.callbacks.History at 0x7f146fbd8bd0>

Evaluate baseline test accuracy and save the model for later usage.

```
_, baseline_model_accuracy = model.evaluate(
test_images, test_labels, verbose=0)
print('Baseline test accuracy:', baseline_model_accuracy)
_, keras_file = tempfile.mkstemp('.h5')
tf.keras.models.save_model(model, keras_file, include_optimizer=False)
print('Saved baseline model to:', keras_file)
```

Baseline test accuracy: 0.9775999784469604 Saved baseline model to: /tmp/tmpjj6swf59.h5

## Fine-tune pre-trained model with pruning

### Define the model

You will apply pruning to the whole model and see this in the model summary.

In this example, you start the model with 50% sparsity (50% zeros in weights) and end with 80% sparsity.

In the comprehensive guide, you can see how to prune some layers for model accuracy improvements.

```
import tensorflow_model_optimization as tfmot
prune_low_magnitude = tfmot.sparsity.keras.prune_low_magnitude
# Compute end step to finish pruning after 2 epochs.
batch_size = 128
epochs = 2
validation_split = 0.1 # 10% of training set will be used for validation set.
num_images = train_images.shape[0] * (1 - validation_split)
end_step = np.ceil(num_images / batch_size).astype(np.int32) * epochs
# Define model for pruning.
pruning_params = {
'pruning_schedule': tfmot.sparsity.keras.PolynomialDecay(initial_sparsity=0.50,
final_sparsity=0.80,
begin_step=0,
end_step=end_step)
}
model_for_pruning = prune_low_magnitude(model, **pruning_params)
# `prune_low_magnitude` requires a recompile.
model_for_pruning.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
model_for_pruning.summary()
```

/tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py:2191: UserWarning: `layer.add_variable` is deprecated and will be removed in a future version. Please use `layer.add_weight` method instead. warnings.warn('`layer.add_variable` is deprecated and ' Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= prune_low_magnitude_reshape (None, 28, 28, 1) 1 _________________________________________________________________ prune_low_magnitude_conv2d ( (None, 26, 26, 12) 230 _________________________________________________________________ prune_low_magnitude_max_pool (None, 13, 13, 12) 1 _________________________________________________________________ prune_low_magnitude_flatten (None, 2028) 1 _________________________________________________________________ prune_low_magnitude_dense (P (None, 10) 40572 ================================================================= Total params: 40,805 Trainable params: 20,410 Non-trainable params: 20,395 _________________________________________________________________

### Train and evaluate the model against baseline

Fine tune with pruning for two epochs.

`tfmot.sparsity.keras.UpdatePruningStep`

is required during training, and `tfmot.sparsity.keras.PruningSummaries`

provides logs for tracking progress and debugging.

```
logdir = tempfile.mkdtemp()
callbacks = [
tfmot.sparsity.keras.UpdatePruningStep(),
tfmot.sparsity.keras.PruningSummaries(log_dir=logdir),
]
model_for_pruning.fit(train_images, train_labels,
batch_size=batch_size, epochs=epochs, validation_split=validation_split,
callbacks=callbacks)
```

Epoch 1/2 WARNING:tensorflow:From /tmpfs/src/tf_docs_env/lib/python3.7/site-packages/tensorflow/python/ops/array_ops.py:5049: calling gather (from tensorflow.python.ops.array_ops) with validate_indices is deprecated and will be removed in a future version. Instructions for updating: The `validate_indices` argument has no effect. Indices are always validated on CPU and never validated on GPU. 3/422 [..............................] - ETA: 12s - loss: 0.0628 - accuracy: 0.9896 WARNING:tensorflow:Callback method `on_train_batch_end` is slow compared to the batch time (batch time: 0.0075s vs `on_train_batch_end` time: 0.0076s). Check your callbacks. 422/422 [==============================] - 5s 9ms/step - loss: 0.0797 - accuracy: 0.9771 - val_loss: 0.0828 - val_accuracy: 0.9790 Epoch 2/2 422/422 [==============================] - 3s 8ms/step - loss: 0.0971 - accuracy: 0.9741 - val_loss: 0.0839 - val_accuracy: 0.9775 <tensorflow.python.keras.callbacks.History at 0x7f12e4502910>

For this example, there is minimal loss in test accuracy after pruning, compared to the baseline.

```
_, model_for_pruning_accuracy = model_for_pruning.evaluate(
test_images, test_labels, verbose=0)
print('Baseline test accuracy:', baseline_model_accuracy)
print('Pruned test accuracy:', model_for_pruning_accuracy)
```

Baseline test accuracy: 0.9775999784469604 Pruned test accuracy: 0.972100019454956

The logs show the progression of sparsity on a per-layer basis.

```
#docs_infra: no_execute
%tensorboard --logdir={logdir}
```

For non-Colab users, you can see the results of a previous run of this code block on TensorBoard.dev.

## Create 3x smaller models from pruning

Both `tfmot.sparsity.keras.strip_pruning`

and applying a standard compression algorithm (e.g. via gzip) are necessary to see the compression
benefits of pruning.

`strip_pruning`

is necessary since it removes every tf.Variable that pruning only needs during training, which would otherwise add to model size during inference- Applying a standard compression algorithm is necessary since the serialized weight matrices are the same size as they were before pruning. However, pruning makes most of the weights zeros, which is added redundancy that algorithms can utilize to further compress the model.

First, create a compressible model for TensorFlow.

```
model_for_export = tfmot.sparsity.keras.strip_pruning(model_for_pruning)
_, pruned_keras_file = tempfile.mkstemp('.h5')
tf.keras.models.save_model(model_for_export, pruned_keras_file, include_optimizer=False)
print('Saved pruned Keras model to:', pruned_keras_file)
```

WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model. Saved pruned Keras model to: /tmp/tmp22u333hk.h5

Then, create a compressible model for TFLite.

```
converter = tf.lite.TFLiteConverter.from_keras_model(model_for_export)
pruned_tflite_model = converter.convert()
_, pruned_tflite_file = tempfile.mkstemp('.tflite')
with open(pruned_tflite_file, 'wb') as f:
f.write(pruned_tflite_model)
print('Saved pruned TFLite model to:', pruned_tflite_file)
```

WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model. INFO:tensorflow:Assets written to: /tmp/tmp51falze0/assets Saved pruned TFLite model to: /tmp/tmpehx5la2i.tflite

Define a helper function to actually compress the models via gzip and measure the zipped size.

```
def get_gzipped_model_size(file):
# Returns size of 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)
```

Compare and see that the models are 3x smaller from pruning.

```
print("Size of gzipped baseline Keras model: %.2f bytes" % (get_gzipped_model_size(keras_file)))
print("Size of gzipped pruned Keras model: %.2f bytes" % (get_gzipped_model_size(pruned_keras_file)))
print("Size of gzipped pruned TFlite model: %.2f bytes" % (get_gzipped_model_size(pruned_tflite_file)))
```

Size of gzipped baseline Keras model: 78211.00 bytes Size of gzipped pruned Keras model: 25797.00 bytes Size of gzipped pruned TFlite model: 24995.00 bytes

## Create a 10x smaller model from combining pruning and quantization

You can apply post-training quantization to the pruned model for additional benefits.

```
converter = tf.lite.TFLiteConverter.from_keras_model(model_for_export)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
quantized_and_pruned_tflite_model = converter.convert()
_, quantized_and_pruned_tflite_file = tempfile.mkstemp('.tflite')
with open(quantized_and_pruned_tflite_file, 'wb') as f:
f.write(quantized_and_pruned_tflite_model)
print('Saved quantized and pruned TFLite model to:', quantized_and_pruned_tflite_file)
print("Size of gzipped baseline Keras model: %.2f bytes" % (get_gzipped_model_size(keras_file)))
print("Size of gzipped pruned and quantized TFlite model: %.2f bytes" % (get_gzipped_model_size(quantized_and_pruned_tflite_file)))
```

WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model. WARNING:tensorflow:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model. INFO:tensorflow:Assets written to: /tmp/tmp6tzu3z87/assets INFO:tensorflow:Assets written to: /tmp/tmp6tzu3z87/assets Saved quantized and pruned TFLite model to: /tmp/tmp0mvlkin1.tflite Size of gzipped baseline Keras model: 78211.00 bytes Size of gzipped pruned and quantized TFlite model: 8031.00 bytes

## See persistence of accuracy from TF to TFLite

Define a helper function to evaluate the TF Lite model on the test dataset.

```
import numpy as np
def evaluate_model(interpreter):
input_index = interpreter.get_input_details()[0]["index"]
output_index = interpreter.get_output_details()[0]["index"]
# Run predictions on ever y 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
```

You evaluate the pruned and quantized model and see that the accuracy from TensorFlow persists to the TFLite backend.

```
interpreter = tf.lite.Interpreter(model_content=quantized_and_pruned_tflite_model)
interpreter.allocate_tensors()
test_accuracy = evaluate_model(interpreter)
print('Pruned and quantized TFLite test_accuracy:', test_accuracy)
print('Pruned TF test accuracy:', model_for_pruning_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. Pruned and quantized TFLite test_accuracy: 0.9722 Pruned TF test accuracy: 0.972100019454956

## Conclusion

In this tutorial, you saw how to create sparse models with the TensorFlow Model Optimization Toolkit API for both TensorFlow and TFLite. You then combined pruning with post-training quantization for additional benefits.

You created a 10x smaller model for MNIST, with minimal accuracy difference.

We encourage you to try this new capability, which can be particularly important for deployment in resource-constrained environments.