我正在使用此repo中的Mask_RCNN包：https://github.com/matterport/Mask_RCNN。
我试图使用这个包来训练我自己的数据集，但一开始它给了我一个错误。
2020-11-30 12:13:16.577252: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1
2020-11-30 12:13:16.587017: E tensorflow/stream_executor/cuda/cuda_driver.cc:314] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
2020-11-30 12:13:16.587075: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (7612ade969e5): /proc/driver/nvidia/version does not exist
2020-11-30 12:13:16.587479: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2020-11-30 12:13:16.593569: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 2300000000 Hz
2020-11-30 12:13:16.593811: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x1b2aa00 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-11-30 12:13:16.593846: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
File "machines.py", line 345, in <module>
model_dir=args.logs)
File "/content/Mask_RCNN/mrcnn/model.py", line 1837, in __init__
self.keras_model = self.build(mode=mode, config=config)
File "/content/Mask_RCNN/mrcnn/model.py", line 1934, in build
anchors = KL.Lambda(lambda x: tf.Variable(anchors), name="anchors")(input_image)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 926, in __call__
input_list)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1117, in _functional_construction_call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/core.py", line 904, in call
self._check_variables(created_variables, tape.watched_variables())
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/core.py", line 931, in _check_variables
raise ValueError(error_str)
ValueError:
The following Variables were created within a Lambda layer (anchors)
but are not tracked by said layer:
<tf.Variable 'anchors/Variable:0' shape=(1, 261888, 4) dtype=float32>
The layer cannot safely ensure proper Variable reuse across multiple
calls, and consquently this behavior is disallowed for safety. Lambda
layers are not well suited to stateful computation; instead, writing a
subclassed Layer is the recommend way to define layers with
Variables.
我查找了导致该问题的代码部分(位于回购中的file: /mrcnn/model.pyline: 1935(：IN[0]: anchors = KL.Lambda(lambda x: tf.Variable(anchors), name="anchors")(input_image)
如果有人知道如何解决，或者已经解决了，请提及解决方案。
转到mrcnn/model.py并添加：
class AnchorsLayer(KL.Layer):
def __init__(self, anchors, name="anchors", **kwargs):
super(AnchorsLayer, self).__init__(name=name, **kwargs)
self.anchors = tf.Variable(anchors)
def call(self, dummy):
return self.anchors
def get_config(self):
config = super(AnchorsLayer, self).get_config()
return config
然后找到行：
anchors = KL.Lambda(lambda x: tf.Variable(anchors), name="anchors")(input_image)
并将其替换为：
anchors = AnchorsLayer(anchors, name="anchors")(input_image)
在TF 2.4中表现得很有魅力！
根本原因：Tensorflow 2.X中Keras Lambda层的bahavior由Tensorflow 1.X改变。在Tensorflow 1.X中的Keras中，所有tf.Variable和tf.get_Variable都会通过变量创建者上下文自动跟踪到layer.weights中，以便它们自动接收梯度并可训练。这种方法在Tensorflow 2.X中将Python代码转换为Execution graph的自动图形编译中存在问题，因此它被删除，现在Lambda层有了检查变量创建并引发错误的代码。简而言之，Tensorflow 2.X中的Lambda层必须是无状态的。如果您想创建变量，Tensorflow 2.X中的正确方法是将层类子类化，并添加可训练权重作为类成员。
解决方案：有2种选择-
-
更改为使用Tensorflow 1.X.。不会引发此错误。
-
用Keras层的子类替换Lambda层：
class AnchorsLayer(tensorflow.keras.layers.Layer):
def __init__(self, anchors):
super(AnchorLayer, self).__init__()
self.anchors_v = tf.Variable(anchors)
def call(self):
return self.anchors_v
# Then replace the Lambda call with this:
anchors_layer = AnchorLayers(anchors)
anchors = anchors_layer()