如何在TensorFlow的熱切執行中使用Keras.applications的ResNeXt？

Question

我正在嘗試從TensorFlow 1.10的Keras應用程序中獲取ResNet101或ResNeXt，由於某種原因它們僅在Keras的存儲庫中可用：

import tensorflow as tf
from keras import applications

tf.enable_eager_execution()

resnext = applications.resnext.ResNeXt101(include_top=False, weights='imagenet', input_shape=(SCALED_HEIGHT, SCALED_WIDTH, 3), pooling=None)

但是，這導致：

Traceback (most recent call last):
  File "myscript.py", line 519, in get_fpn
    resnet = applications.resnet50.ResNet50(include_top=False, weights='imagenet', input_shape=(SCALED_HEIGHT, SCALED_WIDTH, 3), pooling=None)
  File "Keras-2.2.4-py3.5.egg/keras/applications/__init__.py", line 28, in wrapper
    return base_fun(*args, **kwargs)
  File "Keras-2.2.4-py3.5.egg/keras/applications/resnet50.py", line 11, in ResNet50
    return resnet50.ResNet50(*args, **kwargs)
  File "Keras_Applications-1.0.8-py3.5.egg/keras_applications/resnet50.py", line 214, in ResNet50
    img_input = layers.Input(shape=input_shape)
  File "Keras-2.2.4-py3.5.egg/keras/engine/input_layer.py", line 178, in Input
    input_tensor=tensor)
  File "Keras-2.2.4-py3.5.egg/keras/legacy/interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "Keras-2.2.4-py3.5.egg/keras/engine/input_layer.py", line 87, in __init__
    name=self.name)
  File "Keras-2.2.4-py3.5.egg/keras/backend/tensorflow_backend.py", line 529, in placeholder
    x = tf.placeholder(dtype, shape=shape, name=name)
  File "tensorflow/python/ops/array_ops.py", line 1732, in placeholder
    raise RuntimeError("tf.placeholder() is not compatible with "
RuntimeError: tf.placeholder() is not compatible with eager execution.

我從其GitHub master分支安裝了Keras，因為出於某種奇怪的原因，Keras和TensorFlow的Keras API的pip安裝不包括ResNet101，ResNetv2，ResNeXt等。有人知道我如何才能在TensorFlow渴望的情況下運行此類模型（最好是ResNeXt）執行？

Answer 1

如錯誤所示，tf.placeholder（）用作占位符，用於使用feed_dict將數據饋送到tf會話，但與eager模式不兼容。

這個鏈接很好地解釋了一個例子： https : //github.com/tensorflow/tensorflow/issues/18165#issuecomment-377841925

為此，可以使用tf.keras.applications中的模型。 我已經嘗試使用TF2.0 Beta版本。

https://www.tensorflow.org/beta/tutorials/images/transfer_learning#create_the_base_model_from_the_pre-trained_convnets

import tensorflow as tf
resnext = tf.keras.applications.ResNeXt50(weights=None)
print(tf.executing_eagerly())

真正

ResNeXt模型不可用（我必須進行一些更改，例如將resnext.py從keras /應用程序復制到tensorflow / python / keras / applications並更改為__init__.py等），但是如果存在，您可以嘗試使用ResNet50這樣的現有模型他們工作，然后您可以嘗試移植ResNeXt。