Open Rudy112 opened 1 year ago
Hi,
in lib/core/function.py
the iterator i from line 142
https://github.com/svip-lab/HRNet-for-Fashion-Landmark-Estimation.PyTorch/blob/f4ac2e1ef63e08fc51733cdf042b607b41f59261/lib/core/function.py#L142
is reused in line 195
https://github.com/svip-lab/HRNet-for-Fashion-Landmark-Estimation.PyTorch/blob/f4ac2e1ef63e08fc51733cdf042b607b41f59261/lib/core/function.py#L195
So I changed it to j:
for j in range(preds_local.shape[0]):
preds[j] = transform_preds( preds_local[j], c[j], s[j], [config.MODEL.HEATMAP_SIZE[0], config.MODEL.HEATMAP_SIZE[1]] )
Did you resolve the issue with the scalings of the keypoints?
First, thanks for sharing this great work! Here is some issue that I met.
I try to visualize the result by running the script###
the config file is
DATASET: COLOR_RGB: false DATASET: 'deepfashion2' DATA_FORMAT: jpg FLIP: true NUM_JOINTS_HALF_BODY: 8 PROB_HALF_BODY: 0.3 ROOT: 'data/deepfashion2/' ROT_FACTOR: 15 #45 SCALE_FACTOR: 0.1 #0.35 TEST_SET: 'validation' TRAIN_SET: 'train' MINI_DATASET: True SELECT_CAT: [1,2,3,4,5,6,7,8,9,10,11,12,13] MODEL: INIT_WEIGHTS: true NAME: pose_hrnet NUM_JOINTS: 294 PRETRAINED: '' TARGET_TYPE: gaussian IMAGE_SIZE:
I change the CONFIG parameter to True, however it still does not save any image. The image saving only works when I change the BATH_SIZE_PER_GPU to 1. However, the image-saving function is based on a torch grid, thus result in a very wired visualization since the scale of keypoint and output is different. Could you please try to solve the problem? I am using a single GPU RTX 3080TI with Ubuntu 18.04.