Ankan Bhunia

getting NaN loss

12

I tried two datasets that consists of 10k and 30k images respectively. Can you please tell me if I need to change any hyperparameter?

Thanks for your codes. I have some questions. I'd appreciate it if you could respond. 1. I want to understand the evaluation protocol used in the paper to obtain the...

I am trying to use the pretrained models given using the tools/inference.py. python tools/inference.py \ --output_path=/path/to/output \ --checkpoint_path=/path/to/checkpoint \ --test_data_path=/path/to/test/input \ --train/data_path=/path/to/training/data \ --class_embedding_path=/path/to/classs/embeddings \ --n_distribution_path=/path/to/save/n/distribution \ --test_batch_size=4 \ --test_workers=4...

Great Work! Few queries...

1

1. What is the image dimension used for the experiments for each dataset, is it 256x256? 2. Could you please provide the code for FID & LPIPS evaluation? 3. What...