tayama

你是否没有用全部test数据进行测试，我在使用部分测试数据测试时也出现了这个错误，但是使用完整的2000张测试图片就没有这样的问题出现

hi, @youngwanLEE. I use the related code and only change the config-file path(use this pro configs/mimdet_vit_base_mask_rcnn_fpn_sr_0p5_800_1333_4xdec_coco_3x.py), then I got the same result as my input photo, It same like doing...

yes, I use the VToonify-T model, thanks for your advice, and I will try VToonify-D:)

@SimonZeng7108 Can you share your codes? Thanks! :)

When you run inference on ONNX model, the input picture shape should as the same as the shape when you use torch.onnx.export convert .pth to .onnx. Of course, you can...

replace '"train_network.py"' as "train_network.py" in lora_gui.py before subprocess.run(run_cmd)

Sorry, I was so busy last week that I forgot to reply. I just remembered when someone mentioned this question again. First, I change the under directory file "lora_gui.py" 485-487...