features shape

[thormacy]

I am trying to run the model, but there's a error in this line: features = np.concatenate([features_resnet, features_densenet, features_inception], axis=-1) Error is caused by the inconsistent dimensions.

Then I check the shape of features_resnet, features_densenet, features_inception. Find that their shapes are not the same. I pretrain the features using the preprocessing file.

[thormacy]

Thanks for any suggestion

[ypwhs]

可能由于 gluon 的更新，你需要加一个 GlobalAveragePooling。