Shin Donghwan(신동환)

Hi, @wangjiye7. I've faced same problem. first, check a cuda version of build torch. ``` $ python -c 'from torch.utils.collect_env import main; main()' Collecting environment information... PyTorch version: 1.7.0+cu110 Is...

Add following codes at line 330, in tf_pose/estimator.py ``` if tf_config is None: tf_config = tf.ConfigProto() tf_config.gpu_options.allow_growth = True ```

Hi, @mouawiya. Could you tell me your situations detail(environment, which program, etc)?

Hi, @mouawiya First, SFA3D uses the fpn_resnet_18 model and this repository uses the yolov4 model. Two repositories uses different networks. So fpn_resnet_18 is lighter than yolov4, so SFA3D would have...

Hi, @ChaejinE. When call torch.load(), use a parameter(map_location). example code ``` configs.device = torch.device('cpu' if configs.no_cuda else 'cuda:{}'.format(configs.gpu_idx)) model.load_state_dict(torch.load(configs.pretrained_path, map_location=configs.device)) ``` Good Luck. torch.load 함수 호출하실 때, map_location 파라미터를 사용하세요....

Hi^^ you're right. dataset can't download. same dataset link is [this](https://1drv.ms/u/s!Au4J1yd2Q9NvlXntbbKow1QnmpBo?e=c7Aa7R) this is my onedrive.^^ Good Luck^^

? re-try to open link. this link is working.

@sihuiluo Good~!! You're welcome. Good Luck!!

@saisaiwang33 Hi, I checked again now. But I can go to link. Could you try it one more time? or try to do [this](https://drive.google.com/file/d/1XFizLbkpMX0NoPAe1P1WtvVn9KLwbZ7C/view) Good Luck^^

Hi, @darkdante2209. If you want to summary yours video, you should have following data. > 'features' : features of subampled frames in original video > 'picks' : positions of subsampled...