Question about roi_pooling

[AndyLuoJJ]

Hello! I found an error when running your code. I ran python train.py and get this error:

Traceback (most recent call last):
  File "train.py", line 184, in <module>
    net = Net.Alexnet(is_training = True)
  File "/home/au_andyluo/transport/Fast-RCNN-master/Net.py", line 21, in __init__
    self.logits, self.bbox = self.build_network(self.images, self.class_num, self.is_training)
  File "/home/au_andyluo/transport/Fast-RCNN-master/Net.py", line 46, in build_network
    flatten = tf.contrib.layers.flatten(self.roi_pool6, scope='flat_32')
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 183, in func_with_args
    return func(*args, **current_args)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1623, in flatten
    outputs = core_layers.flatten(inputs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/layers/core.py", line 316, in flatten
    return layer.apply(inputs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 805, in apply
    return self.__call__(inputs, *args, **kwargs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 362, in __call__
    outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 720, in __call__
    self._assert_input_compatibility(inputs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1412, in _assert_input_compatibility
    self.name + ' is incompatible with the layer: '
ValueError: Input 0 of layer flatten_1 is incompatible with the layer: its rank is undefined, but the layer requires a defined rank.

And I discovered that the shape of roi_pool6 is unknown, so it cannot be flatten. How can I solve this problem?

[zhanghaobucunzai]

你好！运行您的代码时发现错误。我跑了python train.py，得到这个错误：

Traceback (most recent call last):
  File "train.py", line 184, in <module>
    net = Net.Alexnet(is_training = True)
  File "/home/au_andyluo/transport/Fast-RCNN-master/Net.py", line 21, in __init__
    self.logits, self.bbox = self.build_network(self.images, self.class_num, self.is_training)
  File "/home/au_andyluo/transport/Fast-RCNN-master/Net.py", line 46, in build_network
    flatten = tf.contrib.layers.flatten(self.roi_pool6, scope='flat_32')
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 183, in func_with_args
    return func(*args, **current_args)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1623, in flatten
    outputs = core_layers.flatten(inputs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/layers/core.py", line 316, in flatten
    return layer.apply(inputs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 805, in apply
    return self.__call__(inputs, *args, **kwargs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 362, in __call__
    outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 720, in __call__
    self._assert_input_compatibility(inputs)
  File "/home/au_andyluo/miniconda3/envs/testTensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1412, in _assert_input_compatibility
    self.name + ' is incompatible with the layer: '
ValueError: Input 0 of layer flatten_1 is incompatible with the layer: its rank is undefined, but the layer requires a defined rank.

我发现roi_pool6的形状未知，因此无法展平。我怎么解决这个问题？

请问，这个问题解决了吗