guided-diffusion
guided-diffusion copied to clipboard
openai
I use the following command to test the code python evaluator.py VIRTUAL_imagenet256_labeled.npz VIRTUAL_imagenet256_labeled.npz Inception Score: 338.0111999511719 FID: -3.979039320256561e-13 sFID: -3.865352482534945e-12 is the score right?what might be happen?
How to train the diffusion model on cifar-10? The load_data() function in image_datasets.py can not load cifar-10 datasets directly My train.sh is following: ```shell MODEL_FLAGS="--image_size 32 --num_channels 128 --num_res_blocks 3...
When training classifier_train.py with my own dataset, the loss never drops and the acc is very low!
I trained the classifier on my own dataset, which has a total of 100 images divided into 5 classes with 20 images in each class. Each image is in the...
May I ask if the MODEL FLAGS parameter here can be used to train the diffusion model? Is only one parameter needed for training the diffusion model? 
I am attempting to train a guided diffusion model on my own custom training data. I have successfully trained a model using the improved-diffusion github on my custom data and...
When training using the option `--resume_checkpoint logs/256x256_diffusion.pt`, it always failed training due to `Unexpected key(s) in state_dict` and `size mismatch`. Could you please tell us the hyperparamers of these pretrained...
[The Linear Schedule](https://github.com/openai/guided-diffusion/blob/22e0df8183507e13a7813f8d38d51b072ca1e67c/guided_diffusion/gaussian_diffusion.py#L28) suggests that any number of time-steps are supported. But this is not true, since the [Guided Diffusion](https://github.com/openai/guided-diffusion/blob/22e0df8183507e13a7813f8d38d51b072ca1e67c/guided_diffusion/gaussian_diffusion.py#L136) asserts that all betas are in the interval (0,1). So...
