In [0]:
#@title Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
Welcome to an end-to-end example for magnitude-based weight pruning.
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.
In this tutorial, you will:
tf.keras model for MNIST from scratch.
In [0]:
! pip install -q tensorflow-model-optimization
In [0]:
import tempfile
import os
import tensorflow as tf
import numpy as np
from tensorflow import keras
%load_ext tensorboard
In [0]:
# 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='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,
)
Evaluate baseline test accuracy and save the model for later usage.
In [0]:
_, 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)
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.
In [0]:
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()
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.
In [0]:
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)
For this example, there is minimal loss in test accuracy after pruning, compared to the baseline.
In [0]:
_, 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)
The logs show the progression of sparsity on a per-layer basis.
In [0]:
#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.
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.
First, create a compressible model for TensorFlow.
In [0]:
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)
Then, create a compressible model for TFLite.
In [0]:
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)
Define a helper function to actually compress the models via gzip and measure the zipped size.
In [0]:
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.
In [0]:
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)))
You can apply post-training quantization to the pruned model for additional benefits.
In [0]:
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)))
Define a helper function to evaluate the TF Lite model on the test dataset.
In [0]:
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.
In [0]:
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)
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.