mueller-franzes/medfusion
Implementation of Medfusion - A latent diffusion model for medical image synthesis.
PythonMIT
Issues
- 0
- 1
Enquiry for the amount of the Ds_real / Ds_fake(generated)while you do cal for FID
#28 opened by Kinetics-JOJO - 0
self_cond is not used
#27 opened by PamixSun - 0
Pre-trained model
#26 opened by HeliaHashemipour - 0
class conditional images
#25 opened by tangwy98 - 6
- 3
about memory
#6 opened by Lemonweier - 0
input image name and generate image name
#24 opened by Ystartff - 16
Memorizing training images?
#3 opened by prash-p - 10
Train on my own dataset, and the generated images are all images from my dataset, with strong repeatability
#20 opened by ZZZBBBZZZ - 4
About the first stage and second stage
#23 opened by clearlyzerolxd - 0
- 2
venv problem
#17 opened by LI-CHIN-CHIA - 0
- 2
- 0
RuntimeError: Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [32, 1, 20, 512, 512]
#19 opened by Kidand - 5
Train my own VAE problem
#7 opened by Chopper-233 - 0
convergence speed
#16 opened by TimZhang001 - 0
The loop encounters some issues regarding the shape
#15 opened by YYlin - 3
Train on own dataset
#14 opened by Idea89560041 - 0
Train halfway RuntimeError: The size of tensor a (4) must match the size of tensor b (2) at non-singleton dimension 0
#13 opened by xiaohongzaizhe - 1
- 2
- 5
- 7
Can't sample using pre-trained models
#8 opened by djFatNerd - 2
Do you have other models' weights?
#5 opened by minkyujeon - 0
Pretrained model checkpoints
#4 opened by minkyujeon - 4
- 1
Seeking weights file for the model
#1 opened by parap1uie-s