ziqing
ziqing
Could you provide the pertained classifier for quantitative evaluation of pororo-SV dataset?
In **StoryGAN/code/layers.py** line 23 you miss a 's' `shape = (input_shape[0][0], 1, input_shapes[0][2], input_shapes[0][3])`
### 🐛 Describe the bug ``` ... Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 1024 and using 5 heads. DiffusionWrapper has 865.91 M params. ========================================================================================= No pre-built kernel...
May I ask, do the U-nets used in different denoising steps in the diffusion model share weights?