jahangir

Follow the installation instructions on [densepose](https://github.com/facebookresearch/DensePose/tree/master/tools). Then, use the following command to generate densepose annotations, [](url) python2 tools/infer_simple.py \ --cfg configs/DensePose_ResNet101_FPN_s1x-e2e.yaml \ --output-dir DensePoseData/infer_out/ \ --image-ext [jpg or png] \...

@soumyajit123dev just convert segmented image to numpy array and save as npy

def load_dataset(): for item in dirs: if os.path.isfile(path+item): im = Image.open(path+item) print(im) im = np.array(np.uint8(im)) f, e = os.path.splitext(path+item) np.save("{}.npy".format(f),im) if __name__ == "__main__": load_dataset() ### ### @soumyajit123dev

What do you mean by run dense pose? Clarify please! @mrsahabu

I've used OPENPOSE @soumyajit123dev

> > Thanks for the nice work! > > And we are trying to train the PF-AFN in VITON dataset recently but got the below error in train_PBAFN_stage1. > >...