2 keypoints detection

Hey, thank you for your fast reply.
I tried to run the model for training data with 2 keypoints detection (not human pose estimation), but the loss of the keypoint mask branch is high, and the model does not detect the correct bboxes (regular mask r cnn does and detects very well) do you have any suggestion how transform the current implementation for 2 keypoints detection? (besides changing the number of keypoints of course)

thank you very much

[Superlee506]

L58 in the config.

Yeah, i changed it, but besides that no more changes needed?

[Superlee506]

As far as I know, you just need to modify this place. However you also need to implement your own dataloader.

i tried it, but it still not working well (high loss, really poor detection results)

i tried to use the inspect_humanpose.ipynb for debugging my code, but when i try to Inspect the DetectionKeypointTargetLayer if i use test mode of 'training' the rois, target_bbox, target_bbox, target_keypoint_lables, target_keypoint_weight are all zero, otherwise it throws me the following error:

tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'input_gt_keypoints' with dtype float and shape [?,?,1,3]
[[Node: input_gt_keypoints = Placeholderdtype=DT_FLOAT, shape=[?,?,1,3], _device="/job:localhost/replica:0/task:0/device:GPU:0"]]
[[Node: proposal_targets/rois/_2851 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:

[ShafatRahman]

Hi @Superlee506 ,

By writing a new dataloader do you mean I have to rewrite the load mask function?

[t1t0n]

#35