ds-nat-j

Even I'm facing the same issue, I've used just changed the cloth from a custom dataset and applied cloth-segmentation to get the cloth-mask. I've used the same human model with...

I believe they are working on the GAN inversion part that might be causing this issue.

Also I think it's worth investing time adding code that converts the original tensorflow based stylegan2 pre-trained models from .pkl files to PyTorch .pt files within this repo itself. This...

> I put the picture I downloaded in "Setup Handle Points channel" and the error appears. Is that how it is? Or what's the solution Are you using CPU or...

I'm getting the same issue. Apparently it's happening for all the model zoo models. This is the one that I'm using: `detector = model_zoo.get_model('yolo3_mobilenet1.0_coco', pretrained=False) ` The error: ``` Downloading...

@tengolagan If you can get the jpg, .npy is simply another form, you can use np.asarray(img) ref: https://www.geeksforgeeks.org/how-to-convert-images-to-numpy-array/

@peach6 I think it's something to do with the image size not sure though. I'm able to train on the VITON_traindata dataset which has images of size 192,256. I'm trying...

> @ds-nat-j @peach6 Hi, are you able to resolve this error while training on a custom dataset? If yes, could you please tell me what changes have you made? I...

I second this request @SenHe , I've spent quite a lot of time trying to train this on a larger dataset but I'm getting this error [issue25](https://github.com/SenHe/Flow-Style-VTON/issues/25). No matter how...

Are you able to setup the model retraining code? I don't this this pre-trained model is trained on such data. You might have to build a custom dataset and see...