wj7486

I have some question in gen_image.py

1

Traceback (most recent call last): File "gen_images.py", line 143, in generate_images() # pylint: disable=no-value-for-parameter File "/home/wangjie/anaconda3/envs/torch18/lib/python3.7/site-packages/click/core.py", line 1128, in __call__ return self.main(*args, **kwargs) File "/home/wangjie/anaconda3/envs/torch18/lib/python3.7/site-packages/click/core.py", line 1053, in main rv...

I would like to ask about using the Celeba dataset for my autoencoder kl model that I trained myself .As I want to train 128*128 resolution autoencoderkl model and I...

Hello, excuse me. I would like to ask about using the Celeba dataset for my autoencoder kl model that I trained myself .As I want to train 128*128 resolution autoencoderkl...

fid

2

Dear author, I have a question: Regarding calculating the Fid index, even generating 5000 samples to calculate Fid would take a long time, such as one day. What is the...

weight

4

This is a very good job. Does the author have pre trained token embedding weights on CUB or iNet?

DINO-I

2

Hello, do you have a specific reference code for the indicator dino-i? I am looking forward to your reply

Hello, do you have a specific reference code for the indicator dino-i? The similarity between the real images I calculated is above 0.9, and I am looking forward to your...

dataset issue

1

I would like to confirm the construction of the training data, such as TryOn. According to the training instructions, six fields are required: "edit_image": represents the input image for the...

Hello, do you have a specific reference code for the indicator dino-i? The similarity between the real images I calculated is above 0.9, and I am looking forward to your...