Error: InvalidArgumentError: All dimensions except 2 must match... (on concatenating)

[babak-abad]

I'm programming in python 3.7 via pycharm pro. When I try to train using ssd7_training, I get errors listed below:

Epoch 1/20
Traceback (most recent call last):
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\engine\training_generator.py", line 215, in fit_generator
    class_weight=class_weight)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\engine\training.py", line 1449, in train_on_batch
    outputs = self.train_function(ins)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2979, in __call__
    return self._call(inputs)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2937, in _call
    fetched = self._callable_fn(*array_vals)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\tensorflow_core\python\client\session.py", line 1472, in __call__
    run_metadata_ptr)
tensorflow.python.framework.errors_impl.InvalidArgumentError: All dimensions except 2 must match. Input 2 has shape [16 28800 8] and doesn't match input 0 with shape [16 191040 2].
     [[{{node training/Adam/gradients/predictions/concat_grad/ConcatOffset}}]]

Process finished with exit code -1

Enviroment:

• win 10
• Keras 2.2.5
• tensorflow 1.15.3/ 1.15.2 (I tested both of them)

width/height of image: 1920/1200 channels = 3 number of classes = 2/1 (I tested both of them)

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

[PaulZhangIsing]

Please go to keras_layers/anchor boxes scripts and change the K.image_dim_ordering() == 'tf':(line 171 and line 258 ) to K.image_data_format() == 'channels_last':

I'm programming in python 3.7 via pycharm pro. When I try to train using ssd7_training, I get errors listed below:

Epoch 1/20
Traceback (most recent call last):
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\engine\training_generator.py", line 215, in fit_generator
    class_weight=class_weight)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\engine\training.py", line 1449, in train_on_batch
    outputs = self.train_function(ins)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2979, in __call__
    return self._call(inputs)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2937, in _call
    fetched = self._callable_fn(*array_vals)
  File "E:\Projects\ssd_keras-master\venv\lib\site-packages\tensorflow_core\python\client\session.py", line 1472, in __call__
    run_metadata_ptr)
tensorflow.python.framework.errors_impl.InvalidArgumentError: All dimensions except 2 must match. Input 2 has shape [16 28800 8] and doesn't match input 0 with shape [16 191040 2].
   [[{{node training/Adam/gradients/predictions/concat_grad/ConcatOffset}}]]

Process finished with exit code -1

Enviroment:

* win 10

* Keras                  2.2.5

* tensorflow             1.15.3/ 1.15.2 (I tested both of them)

width/height of image: 1920/1200 channels = 3 number of classes = 2/1 (I tested both of them)