You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi! Keypoint’s location is modeled as a one-hot mask. And it is done with Conv or ConvTranspose layer, where output_channel_size = num_keypoints. I see here: 12
But number of keypoints in DeepFashion2 is different for different classes (for example, in COCO dataset num_keypoints=17). How is this problem solved @geyuying ?
The text was updated successfully, but these errors were encountered:
Hi! Keypoint’s location is modeled as a one-hot mask. And it is done with Conv or ConvTranspose layer, where output_channel_size = num_keypoints. I see here: 12
But number of keypoints in DeepFashion2 is different for different classes (for example, in COCO dataset num_keypoints=17). How is this problem solved @geyuying ?
hi, @amirassov ,
Do you solve the problem and how?
It seems that the deepfashion2_to_coco.py concatenates all 294 keypoints together for each cloth. That is, the maximum number of valid keypoints is only 39(long sleeve outwear). How to handle this unbalance between negative and positive labels?
Hi! Keypoint’s location is modeled as a one-hot mask. And it is done with
Conv
orConvTranspose
layer, whereoutput_channel_size = num_keypoints
. I see here: 1 2But number of keypoints in DeepFashion2 is different for different classes (for example, in COCO dataset num_keypoints=17). How is this problem solved @geyuying ?
The text was updated successfully, but these errors were encountered: