ValueError: Dimension 3 in both shapes must be equal, but are 32 and 64. Shapes are [5,5,3,32] and [5,5,3,64]. for 'Assign' (op: 'Assign') with input shapes: [5,5,3,32], [5,5,3,64].

[dvlab-research]

ValueError: Dimension 3 in both shapes must be equal, but are 32 and 64. Shapes are [5,5,3,32] and [5,5,3,64]. for 'Assign' (op: 'Assign') with input shapes: [5,5,3,32], [5,5,3,64].

[shepnerd]

Try to set --g_cnum 64 when calling test.py. Or you manually set g_cnum to 64 in options/test_options.py.

[Haoru]

Thanks for your help. The results in your paper are fine. And could you tell me how many images in the dataset are used for training?

[shepnerd]

Generally, we follow the train/test splits in the used dataset, and some of them are given in our supplementary file. For celebA-hq-256, 28k images are used for training and 2k for testing.