sriram s
sriram s
Hi, I just have one question. What is the total number of instances? I got 237002 after preprocessing the files downloaded from the above given bollin.inf.ed.uk website. Is that same...
> For anyone who is trying to format the data in the link above, this is what I did to get it in the right format. > > First, I...
Hi @cornerfarmer , Here the code example I used to generated projected 2D key points ``` def project_keypoints_2D(R, T, K, keypoints): ''' K - np.ndarray (3,3) intrinsic parametres R -...
The problem is resolved. Thanks for your response.
Hi, I am facing the similar problem. I have used colmap to generate the poses and --keep_colmap_coord is kept False. So, the output should be in OpenCV coordinate system. The...
@TontonTremblay I am trying to estimate pose of a single object. Following similar approach like yours. But instead of computing the belief map, trying to make the network regress the...
With FP16 quantization, the model performs really well, and the latency is reduced by almost half. However, with INT8 quantization, there’s a significant drop in accuracy. I believe this is...
You can use tensorrt, that is the easiest way. You can also use Pytorch/ONNX quantization toolkit.
Some operation may not be supported by onnx directly. Try using opset 18.