我发现examples/retinaface.cpp中，如果开启OMP加速的话似乎在检测到人脸时会发生内存泄漏，但我定位不了这个问题的具体原因。

值得注意的时，如果将qsort_descent_inplace函数中的OMP指令注释掉这个问题就会消失掉。

static void qsort_descent_inplace(std::vector<FaceObject>& faceobjects, int left, int right)
{
    int i = left;
    int j = right;
    float p = faceobjects[(left + right) / 2].prob;
    ...
    // #pragma omp parallel sections
    {
        // #pragma

Hello, dear Mediapipe guys.

I want to inference the hand pose with Mediapipe model and my own model.

I have my own tf-lite models, it can work on the RGB bitmap.

I try to query the RGB bitmap from input frame with data packet.

My code is

private static final String INPUT_VIDEO_STREAM_NAME = "input_video";
processor.addPacketCallback(INPUT_VIDEO_STREAM_NAME, (packet)->{
 

To get started using this repo quickly using a Google Cloud Platform (GCP) Deep Learning Virtual Machine (VM) follow the instructions below. New GCP users are eligible for a $300 free credit offer. Other quickstart options for this repo include our [Google Colab Notebook](https://colab.research.google.com/github/ultralytics/yolov3/blob

🚀 Feature request

Current Behavior

flow(
    SomeIOType.decode,
    ... etc
)

Accessing .decode of a type by passing it, causes lint warning:
warning Avoid referencing unbound methods which may cause unintentional scoping of this @typescript-eslint/unbound-method

However the function is specifically bound: this.decode = this.decode.bind(this);

Desi

When attempting to download cityscapes_2048x1024 I got: ./download-models.sh: line 721: download_fcn_resnet18_cityscapes_2048x512: command not found
It looks like there was a typo, and line 721 needs to be changed from:
download_fcn_resnet18_cityscapes_2048x512 to download_fcn_resnet18_cityscapes_2048x1024

Thanks for the amazing repo!

Problem to Solve

At the moment Grakn user of the Docker container may not know how to capture logs from inside a running docker container - especially important when the run has failed.

Current Workaround

There may not be a clean one, but in a case, we could log into the docker container:

$ docker exec -it [container id] /bin/bash
$ cd /path/to/logs
$ [some how upload via 

The dldt/get-started-linux.md documented references <DLDT_DIR>/inference-engine/samples/sample_data in several places, but I'm not able to find that directory or any references to it except in the documentation.

Hi NVIDIA Team,

To make this project successful, I would like to suggest to add few things. I would love to assist on this.

1. Complete technical installation steps to add more values
2. Details of all pre-requisites, to build this project successfully.
3. Overall technical background, design and architecture. Just like we provide a technical guide and documentation for other software engine

https://www.usenix.org/conference/opml19/program

Prepare to read papers

https://github.com/awslabs/mxnet-model-server/blob/master/plugins/endpoints/src/main/java/software/amazon/ai/mms/plugins/endpoint/ExecutionParameters.java#L26

'max_request_size' seems to refer to bytes, not mb.

Link

https://github.com/tucan9389/MLProblem-MLFramework-for-iOS-template-project