The video-cyclegan from nudro

video-cyclegan's Introduction

Hi there 👋

🔭 I’m currently working on multi-modal image translation with GANs and most recently, DDPMs.
🌱 Other areas of research include chronic pain (affective) multimodal detection, and classical tasks like image registration.
📫 How to reach me: [email protected]
😄 Pronouns: she/her

video-cyclegan's People

Contributors

Stargazers

Watchers

video-cyclegan's Issues

Apply pix2pix model

Hi, Thank you for the great work.

I use this repository to train a pix2pix model, I want to use my checkpoints to test your work.

After replacing your latest_net_G.pth with mine and run command: python main.py --name summer2winter_yosemite_pretrained --model test --preprocess none --no_dropout, I got this error:

----------------- Options ---------------
         	aspect_ratio: 1.0                      	 
           	batch_size: 1                        	 
      	checkpoints_dir: ./checkpoints            	 
            	crop_size: 256                      	 
             	dataroot: None                     	 
         	dataset_mode: single                   	 
            	direction: AtoB                     	 
      	display_winsize: 256                      	 
                	epoch: latest                   	 
                 	eval: False                    	 
              	gpu_ids: 0                        	 
            	init_gain: 0.02                     	 
            	init_type: normal                   	 
             	input_nc: 3                        	 
              	isTrain: False                    		 [default: None]
            	load_iter: 0                        		 [default: 0]
            	load_size: 256                      	 
     	max_dataset_size: inf                      	 
                	model: test                     	 
         	model_suffix:                          	 
           	n_layers_D: 3                        	 
                 	name: summer2winter_yosemite_pretrained    [default: experiment_name]
                  	ndf: 64                       	 
                 	netD: basic                    	 
                 	netG: resnet_9blocks           	 
                  	ngf: 64                       	 
           	no_dropout: True                     		 [default: False]
              	no_flip: False                    	 
                 	norm: instance                 	 
             	num_test: 50                       	 
          	num_threads: 4                        	 
            	output_nc: 3                        	 
                	phase: test                     	 
           	preprocess: none                     		 [default: resize_and_crop]
          	results_dir: ./results/               	 
       	serial_batches: False                    	 
               	suffix:                          	 
              	verbose: False                    	 
----------------- End -------------------
initialize network with normal
model [TestModel] was created
loading the model from ./checkpoints/summer2winter_yosemite_pretrained/latest_net_G.pth
Traceback (most recent call last):
  File "main.py", line 23, in <module>
	model.setup(opt)           	# regular setup: load and print networks; create schedulers
  File "/home/lk3696/cyclegan_video/video-cyclegan/models/base_model.py", line 88, in setup
	self.load_networks(load_suffix)
  File "/home/lk3696/cyclegan_video/video-cyclegan/models/base_model.py", line 198, in load_networks
	self.__patch_instance_norm_state_dict(state_dict, net, key.split('.'))
  File "/home/lk3696/cyclegan_video/video-cyclegan/models/base_model.py", line 174, in __patch_instance_norm_state_dict
	self.__patch_instance_norm_state_dict(state_dict, getattr(module, key), keys, i + 1)
  File "/home/lk3696/cyclegan_video/video-cyclegan/models/base_model.py", line 174, in __patch_instance_norm_state_dict
	self.__patch_instance_norm_state_dict(state_dict, getattr(module, key), keys, i + 1)
  File "/home/lk3696/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 778, in __getattr__
	raise ModuleAttributeError("'{}' object has no attribute '{}'".format(
torch.nn.modules.module.ModuleAttributeError: 'Sequential' object has no attribute 'model'

I try to change netG: resnet_9blocks to netG: unet_256 in test_opt.txt, but I still got same error.

May i have your suggestions to use pix2pix model?
Any help is much appreciated:)

Recommend Projects