few-shot-diffusion-models
few-shot-diffusion-models copied to clipboard
georgosgeorgos
Few-Shot Diffusion Models
Thank you for your excellent work. I would like to ask how to specify the category of the generated image during the sampling process. Is it by using the relevant...
few-shot-diffusion-models/dataset/base.py", line 95, in get_data residual = self.img_cls - value.shape[0] AttributeError: 'list' object has no attribute 'shape' Could you please provide the data file?
There are some inconsistencies between the code and the contents of the readme file.
It seems that the requirements.txt need some local files. Could you please check the requirements.txt and modify its content?
There is no `run.sh` script in the scripts folder. There is only one `main.sh` script. Is it the `run.sh` document? I renamed `main.sh` to `run.sh`, and then run ` bash...
Im `vfsddpm.py` line 223-225: `x_set_tmp = batch[:, ix]` yout select `ns - 1` of data, but you don't select `ns-1` t_emd, that cause `vitset.py` line 176 :`t_emb = t_emb.view(b, ns,...
In `vit.py` in `forward_set` function the transform module is being used twice in 1 forward evaluation. First the common forward https://github.com/georgosgeorgos/few-shot-diffusion-models/blob/8bba697caa39d208b471e46e05daf5cc176f0c37/model/vit.py#L200-L201 Second during `mean_patch` pooling https://github.com/georgosgeorgos/few-shot-diffusion-models/blob/8bba697caa39d208b471e46e05daf5cc176f0c37/model/vit.py#L220-L225 Is this intended?
Is there a plan to release pre-trained weights so that sampling/evaluation can be done without re-training everything from scratch?
Can you provide the details about the metrics computation? I found the code in the following run file: https://github.com/georgosgeorgos/few-shot-diffusion-models/blob/f9e86f72aac6d0d34a76bb637498ab1af2ae5db9/script/compute_fid.sh#L117 Looks like the two '.npz' files are all full_samples_conditional_10000x32x32x3_in-distro_5.npz, how you...
