我将训练我的模型量化意识。但是,当我使用它时,tensorflow_model_optimization不能量化tf.reshape函数,并抛出一个错误。
'2.4.0-dev20200903'
守则:
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '3'
from tensorflow.keras.applications import VGG16
import tensorflow_model_optimization as tfmot
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
quantize_model = tfmot.quantization.keras.quantize_model
inputs = keras.Input(shape=(784,))
# img_inputs = keras.Input(shape=(32, 32, 3))
dense = layers.Dense(64, activation="relu")
x = dense(inputs)
x = layers.Dense(64, activation="relu")(x)
outputs = layers.Dense(10)(x)
outputs = tf.reshape(outputs, [-1, 2, 5])
model = keras.Model(inputs=inputs, outputs=outputs, name="mnist_model")
# keras.utils.plot_model(model, "my_first_model.png")
q_aware_model = quantize_model(model)以及产出:
Traceback (most recent call last):
File "<ipython-input-39-af601b78c010>", line 14, in <module>
q_aware_model = quantize_model(model)
File "/home/essys/.local/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/quantize.py", line 137, in quantize_model
annotated_model = quantize_annotate_model(to_quantize)
File "/home/essys/.local/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/quantize.py", line 210, in quantize_annotate_model
to_annotate, input_tensors=None, clone_function=_add_quant_wrapper)
...
File "/home/essys/anaconda3/envs/tf_gpu/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py", line 667, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in user code:
TypeError: tf__call() got an unexpected keyword argument 'shape'如果有人知道,请帮忙?
发布于 2020-09-10 06:51:05
背后的原因是因为您的层目前还不支持QAT。如果你想量化它,你必须自己用quantize_annotate_layer写你的量化,然后通过quantize_scope传递它,然后用quantize_apply应用到你的模型中,如这里描述的:https://www.tensorflow.org/model_optimization/guide/quantization/training_comprehensive_guide?hl=en#quantize_custom_keras_layer。
我已经以batch_norm_layer为例在here中创建了一个
对于QAT层,Tensorflow 2.x是不完整的,请考虑在操作符后面添加FakeQuant来使用tf1.x。
https://stackoverflow.com/questions/63737440
复制相似问题