orydatadudes
orydatadudes
hey, i follow [training](https://github.com/svip-lab/impersonator/blob/master/doc/train.md) process so i download all files including smpls folder my question is : what i have under that folder what inside kps.pkl and pose_shape.pkl? how i...
hello, you used [OpenPose](https://github.com/Hzzone/pytorch-openpose) to create pose *.txt files how i can create thous files for another data set ? i follow the link for OpenPose but i i can't...
hey when i train the model from random weights during the training i can see some results ( every N epochs) when i run test.py with the new trained models...
when run test.sh i get he following error File "/home/projects/ADGAN/test.py", line 44, in print(len(dataset)) File "/homeprojects/ADGAN/data/custom_dataset_data_loader.py", line 40, in __len__ return min(len(self.dataset), self.opt.max_dataset_size) TypeError: 'NoneType' object cannot be interpreted as...
when init the class SMPLXLayer and adding more features - changing False to True class SMPLXLayer(SMPLX): def __init__( self, *args, **kwargs ) -> None: super(SMPLXLayer, self).__init__( create_global_orient=False, create_body_pose=False, create_left_hand_pose=False, create_right_hand_pose=False,...
hey thanks for your work! i checked some of the **test** images (more specific fashionMENShirts_Polosid0000180202_4full.jpg) i got very good results  i was very impressed by the ability of the...
thank you for your work can i use the auto encoder to remove noise/blur from images? in the paper i can see the following example  so...
Hi i used the photos of the dog from the paper  after training the model (took about 1 hour) i try to generate new images "a photo of...
when i run test.py i got the following results  i also got wearning when tried to load the model utils-> load_network load with strict = True didn't succeed :...
when i run download_models.py i am getting following error "urllib.error.HTTPError: HTTP Error 403: Forbidden" so i can't download vgg19/16 can i download it from another place and them just load...