Hi Superlee,
thank you for your great work. I have a question about your keypoint mask head (build_fpn_keypoint_mask_graph).
As far as I can tell there are differences between yours the keypoint mask head discribed in the mask r-cnn paper. For example you used KEYPOINT_MASK_POOL_SIZE= 7 instead of KEYPOINT_MASK_POOL_SIZE= 14. You also used the deconv layer to reduce the feature map depth to num_keypoints.
Is there a certain reason for these changes?
In the picture you can see the head structure after those 8 conv layers.
Thanks,
Lukas
Hi Superlee,
thank you for your great work. I have a question about your keypoint mask head (build_fpn_keypoint_mask_graph).
As far as I can tell there are differences between yours the keypoint mask head discribed in the mask r-cnn paper. For example you used
KEYPOINT_MASK_POOL_SIZE= 7instead ofKEYPOINT_MASK_POOL_SIZE= 14. You also used the deconv layer to reduce the feature map depth tonum_keypoints.Is there a certain reason for these changes?
In the picture you can see the head structure after those 8 conv layers.
Thanks,
Lukas