search

Gait3D / Gait3D-Benchmark

This is the code for the paper "Gait Recognition in the Wild with Dense 3D Representations and A Benchmark. (CVPR 2022)", "Gait Recognition in the Wild with Multi-hop Temporal Switch", and "Parsing is All You Need for Accurate Gait Recognition in the Wild".
133 stars 19 forks source link

about heatMap in Fig.6 ("Gait Recognition in the Wild with Multi-hop Temporal Switch") #17

Closed Au21ke closed 1 year ago

Au21ke commented 1 year ago

Sorry to bother you, can you briefly share how you got the gait heatmap?

JinkaiZheng commented 1 year ago

Hi~ You can output one layer from the network directly, let's say X1. Then, use cv2.resize to resize X1 to X2 (size: 64x44). Finally, employ cv2.applyColorMap(X2, cv2.COLORMAP JET) to get the heatmap.