Activity Regularizer 不适用于量化感知训练 (QAT)。
TypeError：函数构建代码之外的操作正在传递一个“图形”张量。
这仅发生在量化模型上，非量化模型对活动正则化损失具有 numpy 值。模型损失，即正则化损失应该在没有空张量/占位符的情况下累积。并且在急切模式下执行时应该能够在图形之外对它们进行操作。
目前，活动正则化损失张量是<class 'tensorflow.python.framework.ops.Tensor'>没有 numpy 值的类型，偏差正则化张量也是 tf.tensor 但确实带有 numpy 值。但我不确定这是否会引发错误，我无法对 tf op 进行操作。
重现问题的代码
import numpy as np
import tensorflow as tf
from tensorflow_model_optimization.python.core.quantization.keras import quantize
from tensorflow.python import keras
l = tf.keras.layers
tf.config.run_functions_eagerly(True)
def functional_model():
"""Builds an MNIST functional model."""
inp = tf.keras.Input(shape=image_input_shape())
x = l.Conv2D(filters=32, kernel_size=5, padding='same', activation='relu',
kernel_regularizer=tf.keras.regularizers.l2(l=0.0001))(inp)
x = tf.keras.layers.ActivityRegularization(l2=0.0001)(x)
x = l.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(x)
# TODO(pulkitb): Add BatchNorm when transformations are ready.
# x = l.BatchNormalization()(x)
x = l.Conv2D(filters=64, kernel_size=5, padding='same', activation='relu',
kernel_regularizer=tf.keras.regularizers.l2(l=0.0001))(x)
x = tf.keras.layers.ActivityRegularization(l2=0.0001)(x)
x = l.MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding='same')(x)
x = l.Flatten()(x)
x = l.Dense(1024, activation='relu')(x)
x = l.Dropout(0.4)(x)
out = l.Dense(10, activation='softmax')(x)
return tf.keras.Model(inp, [out])
def image_input_shape(img_rows=28, img_cols=28):
if tf.keras.backend.image_data_format() == 'channels_first':
return 1, img_rows, img_cols
else:
return img_rows, img_cols, 1
def preprocessed_data(img_rows=28,
img_cols=28,
num_classes=10):
"""Get data for mnist training and evaluation."""
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()
if tf.keras.backend.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
# convert class vectors to binary class matrices
y_train = tf.keras.utils.to_categorical(y_train, num_classes)
y_test = tf.keras.utils.to_categorical(y_test, num_classes)
return x_train, y_train, x_test, y_test
model = functional_model()
model.summary()
x_train, y_train, x_test, y_test = preprocessed_data()
model.compile(
loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=500)
_, model_accuracy = model.evaluate(x_test, y_test, verbose=0)
print("Quantizing model")
quantized_model = quantize.quantize_model(model)
print(quantized_model.losses)
quantized_model.compile(
loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
print(quantized_model.losses)
quantized_model.fit(x_train, y_train, batch_size=500)
_, quantized_model_accuracy = quantized_model.evaluate(
x_test, y_test, verbose=0)
错误输出
120/120 [==============================] - 3s 19ms/step - loss: 2.1668 - accuracy: 0.3804
Quantizing model
[<tf.Tensor: shape=(), dtype=float32, numpy=0.00022464147>, <tf.Tensor 'activity_regularization/ActivityRegularizer/truediv:0' shape=() dtype=float32>, <tf.Tensor: shape=(), dtype=float32, numpy=0.0042893193>, <tf.Tensor 'activity_regularization_1/ActivityRegularizer/truediv:0' shape=() dtype=float32>]
[<tf.Tensor: shape=(), dtype=float32, numpy=0.00022464147>, <tf.Tensor 'activity_regularization/ActivityRegularizer/truediv:0' shape=() dtype=float32>, <tf.Tensor: shape=(), dtype=float32, numpy=0.0042893193>, <tf.Tensor 'activity_regularization_1/ActivityRegularizer/truediv:0' shape=() dtype=float32>]
Traceback (most recent call last):
File "/home/user/git/archive-code/tempTrain.py", line 80, in <module>
quantized_model.fit(x_train, y_train, batch_size=500)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/keras/engine/training.py", line 1184, in fit
tmp_logs = self.train_function(iterator)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/keras/engine/training.py", line 853, in train_function
return step_function(self, iterator)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/keras/engine/training.py", line 842, in step_function
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py", line 1286, in run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py", line 2849, in call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/distribute/distribute_lib.py", line 3632, in _call_for_each_replica
return fn(*args, **kwargs)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py", line 597, in wrapper
return func(*args, **kwargs)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/keras/engine/training.py", line 835, in run_step
outputs = model.train_step(data)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/keras/engine/training.py", line 789, in train_step
y, y_pred, sample_weight, regularization_losses=self.losses)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/keras/engine/compile_utils.py", line 231, in __call__
reg_loss = tf.add_n(regularization_losses)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py", line 206, in wrapper
return target(*args, **kwargs)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 4000, in add_n
return gen_math_ops.add_n(inputs, name=name)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 392, in add_n
inputs, name=name, ctx=_ctx)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 425, in add_n_eager_fallback
ctx=ctx, name=name)
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/eager/execute.py", line 75, in quick_execute
raise e
File "/home/user/TF2_6Venv/lib/python3.6/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
inputs, attrs, num_outputs)
TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
@tf.function
def has_init_scope():
my_constant = tf.constant(1.)
with tf.init_scope():
added = my_constant * 2
The graph tensor has name: activity_regularization/ActivityRegularizer/truediv:0
系统信息
TensorFlow 版本（从源代码或二进制安装）：TF 2.6
TensorFlow 模型优化版本（从源代码或二进制安装）：pip install
Python版本：3.6.9