poddo

ONet训练结果和模型测试不是很好？

2

  贴两张训练ONet的结果图和用ONet模型去测试的结果图，感觉loss还是很高，检测人脸也有误框，还有人脸关键点好像没有检测出来，是哪里的问题呢？

Train Error.

3

Hi, i met the error when i train my own data and the error like this: Traceback (most recent call last): File "trainval_net.py", line 484, in rois_label = _RCNN(im_data, im_info,...

TypeError: ONNX node of type Shape is not supported.

13

i have redefine the layer type like prelu and Transpose, when i run convertCaffe.py and i get error like this.  my env is ubuntu16.04, pytorch 1.3.0 and torchvision 0.3.0.

相机焦距F的值是怎么确定的？

3

https://github.com/VShawn/Shawn_pose_estimation_by_opencv/blob/ca5010deb64b7d9ec0e7c17451d27bf8cd2c9b8e/%E7%9B%B8%E6%9C%BA%E4%BD%8D%E5%A7%BF%E4%BC%B0%E8%AE%A13%EF%BC%9A%E6%A0%B9%E6%8D%AE%E4%B8%A4%E5%B9%85%E5%9B%BE%E5%83%8F%E7%9A%84%E4%BD%8D%E5%A7%BF%E4%BC%B0%E8%AE%A1%E7%BB%93%E6%9E%9C%E6%B1%82%E6%9F%90%E7%82%B9%E7%9A%84%E4%B8%96%E7%95%8C%E5%9D%90%E6%A0%87/main3.cpp#L9 你好，请问下相机的内参参数中包含焦距fx和fy，那这个焦距F是怎么得到的呢这两个焦距之间有什么关系吗？

evaluation.py error

6

hi, thanks for you share. First i run this command: python setup.py build_ext --inplace and then i run: **python evaluation.py -p widerface_txt/ -g ground_truth/** i get error like this: ImportError:...

hello, it's a good job and thanks for you sharing. when i prepare the data and run the command "python tools/data_converter/nuscenes_converter.py --data-root /data/public/datasets/nuscenes", i met the error like this: from...

Your work has been a great help for a beginner, but I don’t understand how to visualize the results obtained? Hope to get your reply, thank you again for your...

input and target mismatch

1

ghm_loss.py", line 55, in _custom_loss_grad return torch.sigmoid(x).detach() - target RuntimeError: The size of tensor a (2) must match the size of tensor b (208) at non-singleton dimension 1 hi, my...

Seeing ssd mobilenet.param and the code only extract a value detection_out, then the pytorch model is transferred to the ncnn model, do we need to concat prob and loc? plz...