使用 yolo4.cfg 进行 tensorflow 2.2 训练中的形状不匹配问题

Question

I recently added a new feature to my yolov3 implementation which is models are currently loaded directly from DarkNet cfg files for convenience, I tested the code with yolov3 configuration as well as yolov4 configuration they both work just fine except for v4 training. Shortly after I start training I get a shapes mismatch error and I'll be very grateful if someone can help me get rid of the error and get to finally complete my project. Please let me know in the comments and I will provide you with any resources you need to help me with fixing the problem and thank you in advance...

This is what I run in order to reproduce:

if __name__ == '__main__':
    tr = Trainer((608, 608, 3),
                 '../Config/yolo4.cfg',
                 '../Config/beverly_hills.txt',
                 1344, 756, score_threshold=0.1,
                 train_tf_record='../Data/TFRecords/beverly_hills_train.tfrecord',
                 valid_tf_record='../Data/TFRecords/beverly_hills_test.tfrecord')

    tr.train(
        100,
        8,
        1e-3,
        dataset_name='beverly_hills',
        merge_evaluation=False,
        n_epoch_eval=10,
        clear_outputs=True
    )
L

links to files you need:

• bh_labels.csv (794 Kb)
• beverly_hills.txt (162 B)
• beverly_hills_train.tfrecord (509 Mb)
• beverly_hills_test.tfrecord (89 Mb)

Here is the error message:

Traceback (most recent call last):
  File "trainer.py", line 629, in <module>
    clear_outputs=True
  File "../Helpers/utils.py", line 62, in wrapper
    result = func(*args, **kwargs)
  File "trainer.py", line 490, in train
    validation_data=valid_dataset,
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 108, in _method_wrapper
    return method(self, *args, **kwargs)
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1090, in fit
    tmp_logs = train_function(iterator)
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 766, in __call__
    result = self._call(*args, **kwds)
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py", line 826, in _call
    return self._stateless_fn(*args, **kwds)
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 2811, in __call__
    return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1838, in _filtered_call
    cancellation_manager=cancellation_manager)
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 1914, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/function.py", line 549, in call
    ctx=ctx)
  File "/root/.local/lib/python3.6/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
    inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError:  Incompatible shapes: [4,76,76,3,1] vs. [4,19,19,3,1]
     [[node yolo_loss/logistic_loss/mul (defined at ../Helpers/utils.py:260) ]] [Op:__inference_train_function_38735]

Errors may have originated from an input operation.
Input Source operations connected to node yolo_loss/logistic_loss/mul:
 yolo_loss/split_1 (defined at ../Helpers/utils.py:222) 
 yolo_loss/split (defined at ../Helpers/utils.py:196)

Function call stack:
train_function

And when I change the batch_size to 8 instead of 4, the error mutates into the following(the error source changes):

Traceback (most recent call last):
  File "/Users/emadboctor/Desktop/Code/yolov3-keras-tf2/Main/trainer.py", line 693, in <module>
    clear_outputs=True,
  File "/Users/emadboctor/Desktop/Code/yolov3-keras-tf2/Helpers/utils.py", line 62, in wrapper
    result = func(*args, **kwargs)
  File "/Users/emadboctor/Desktop/Code/yolov3-keras-tf2/Main/trainer.py", line 526, in train
    validation_data=valid_dataset,
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 66, in _method_wrapper
    return method(self, *args, **kwargs)
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 848, in fit
    tmp_logs = train_function(iterator)
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 580, in __call__
    result = self._call(*args, **kwds)
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/def_function.py", line 644, in _call
    return self._stateless_fn(*args, **kwds)
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 2420, in __call__
    return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 1665, in _filtered_call
    self.captured_inputs)
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 1746, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 598, in call
    ctx=ctx)
  File "/usr/local/lib/python3.7/site-packages/tensorflow/python/eager/execute.py", line 60, in quick_execute
    inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError:  Incompatible shapes: [8,13,13,3,2] vs. [8,52,52,3,2]
     [[node gradient_tape/yolo_loss/sub_5/BroadcastGradientArgs (defined at Users/emadboctor/Desktop/Code/yolov3-keras-tf2/Main/trainer.py:526) ]] [Op:__inference_train_function_42744]

Function call stack:
train_function

Answer 1

Adding this line in models.py solved the shapes problem and the training started as expected:

if '4' in self.model_configuration:
    self.output_layers.reverse()