issue with reducing the number of stages

[M-E-Williams]

Hi,

If I truncate the number of stages I get the following error (included at the bottom of the post) I have altered the number of losses to reflect the number of stages. Notably the number of numpy arrays expected is always 2* the number of stages, whereas 12 numpy arrays are always presented. There are no pretrained weights for the stage blocks

Traceback (most recent call last): File "train_pose_ownmod.py", line 172, in initial_epoch=last_epoch File "/usr/local/lib/python3.5/dist-packages/keras/legacy/interfaces.py", line 87, in wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 2114, in fit_generator class_weight=class_weight) File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 1826, in train_on_batch check_batch_axis=True) File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 1411, in _standardize_user_data exception_prefix='target') File "/usr/local/lib/python3.5/dist-packages/keras/engine/training.py", line 88, in _standardize_input_data '...') ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 6 array(s), but instead got the following list of 12 arrays: [array([[[[ 0. , 0. , 0. , ..., 0. , 0. , 0. ], [ 0. , 0. , 0. , ..., 0. , 0. , 0. ...

[anatolix]

Data generator supply ground truth to each stage to get loss on each stage. Reduce number of ground truths (and masks too) in input params and generator.

[Yukicuc]

@anatolix how to reduce the input params and generator? i'm sorry for asking it cause i don't find the solution.

[Yukicuc]

oh!, i find it!!

[xiaofeiwu]

@Yukicuc Could you explain the solution? I met similar problem and didn't resolve it so far.

[xiaofeiwu]

OK. Now I found the related code in ds_generator_client.py. The groundtruth should be revised following the number of stages.