Open StartHua opened 7 months ago
hi bro can you help me to fix the issue
Namespace(gpu_ids='0', workers=4, batch_size=1, fp16=False, cuda='True', test_name='test', dataroot='.././kaggle/working/data/', datamode='test', data_list='pairs7.txt', output_dir='.././kaggle/working/output/', datasetting='unpaired', fine_width=768, fine_height=1024, tensorboard_dir='./data/zalando-hd-resize/tensorboard', checkpoint_dir='checkpoints', tocg_checkpoint='./eval_models/weights/v0.1/mtviton.pth', gen_checkpoint='./eval_models/weights/v0.1/gen.pth', tensorboard_count=100, shuffle=False, semantic_nc=13, output_nc=13, gen_semantic_nc=7, warp_feature='T1', out_layer='relu', clothmask_composition='warp_grad', upsample='bilinear', occlusion=True, norm_G='spectralaliasinstance', ngf=64, init_type='xavier', init_variance=0.02, num_upsampling_layers='most')
Start to test %s!
/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py:558: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
warnings.warn(_create_warning_msg(
Network [SPADEGenerator] was created. Total number of parameters: 100.5 million. To see the architecture, do print(network).
Error occurred: Input and output must have the same number of spatial dimensions, but got input with spatial dimensions of [1024, 768, 3] and output size of (256, 192). Please provide input tensor in (N, C, d1, d2, ...,dK) format and output size in (o1, o2, ...,oK) format.
Traceback (most recent call last):
File "/content/HR-VITON/test_generator.py", line 282, in
I used own 768*1024 jpg images but it show above error can you guide me how to use own image and also own image what type of metadata use like [RGB vs BGR]
Error occurred: Input and output must have the same number of spatial dimensions, but got input with spatial dimensions of [1024, 768, 3] and output size of (256, 192). Please provide input tensor in (N, C, d1, d2, ...,dK) format and output size in (o1, o2, ...,oK) format.