Raaj

Sometimes in very complex networks, its hard to see where the layer we are hovering over is connected to. If you can bolden the line between the connected layer and...

``` net.setBlob(".data", inputBlob); // フォワードパス(順伝播)の計算 net.forward(); // 出力層(Softmax)の出力を取得, ここに予測結果が格納されている const cv::dnn::Blob prob = net.getBlob("prob"); // Blobオブジェクト内部のMatオブジェクトへの参照を取得 // ImageNet 1000クラス毎の確率が格納された1x1000の行列(ベクトル) const cv::Mat probMat = prob.matRefConst(); ``` I notice in this code...

Does this work on meshes only or can it work with an unorganized RGBXYZ Pointcloud?

2

I would also like to know what kind of runtime performance we get with this

Good day, I am trying to understand the TripletImageLoader It seems that you are already forming/forcing the an anchor/positive pair to be paired with only a fixed negative datapoint. For...

Invalid Index of 0-dim tensor

2

losses.update(loss_triplet.data[0], data1.size(0)) IndexError: invalid index of a 0-dim tensor. Use tensor.item() to convert a 0-dim tensor to a Python number

Since this is a solid state LIDAR, it should have a depth resolution. What is that resolution? Or is this LIDAR adaptive in nature?

``` Ceres Solver Report: Iterations: 28, Initial cost: 3.123784e-01, Final cost: 1.621738e-01, Termination: CONVERGENCE Ceres Solver Report: Iterations: 5, Initial cost: 1.616343e-01, Final cost: 1.326836e-01, Termination: CONVERGENCE Ceres Solver Report:...

Dataset

1

Where can I get the data: ../data/train/train_data.json is missing

### Checklist - [X] I have searched related issues but cannot get the expected help. - [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but cannot get the expected help....