From 0bfe4fe408fc253b32040e96af18665a3916391f Mon Sep 17 00:00:00 2001 From: DefTruth Date: Mon, 20 Sep 2021 21:16:36 +0800 Subject: [PATCH 1/2] Add C++ Demo link --- README.md | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/README.md b/README.md index 7ce02b0..2995783 100644 --- a/README.md +++ b/README.md @@ -217,6 +217,13 @@ Speed is measured with `inference_speed_test.py` for reference. * Note 2: GPUs before Turing architecture does not support FP16 inference, so GTX 1080 Ti uses FP32. * Note 3: We only measure tensor throughput. The provided video conversion script in this repo is expected to be much slower, because it does not utilize hardware video encoding/decoding and does not have the tensor transfer done on parallel threads. If you are interested in implementing hardware video encoding/decoding in Python, please refer to [PyNvCodec](https://github.com/NVIDIA/VideoProcessingFramework). +
+ +## Third-party Resources + +* NCNN C++ and Android Demo: [ncnn_Android_RobustVideoMatting](https://github.com/FeiGeChuanShu/ncnn_Android_RobustVideoMatting) from [FeiGeChuanShu](https://github.com/FeiGeChuanShu) +* ONNXRuntime C++ Demo: [lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit/blob/main/ort/cv/rvm.cpp) from [DefTruth](https://github.com/DefTruth) +
## Project Members From 1431b38feae077301051acdf130b88a729f908e6 Mon Sep 17 00:00:00 2001 From: DefTruth Date: Tue, 21 Sep 2021 01:32:09 +0800 Subject: [PATCH 2/2] Add C++ Demo link --- README.md | 2 +- README_zh_Hans.md | 8 +++++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 2995783..9a2c20d 100644 --- a/README.md +++ b/README.md @@ -222,7 +222,7 @@ Speed is measured with `inference_speed_test.py` for reference. ## Third-party Resources * NCNN C++ and Android Demo: [ncnn_Android_RobustVideoMatting](https://github.com/FeiGeChuanShu/ncnn_Android_RobustVideoMatting) from [FeiGeChuanShu](https://github.com/FeiGeChuanShu) -* ONNXRuntime C++ Demo: [lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit/blob/main/ort/cv/rvm.cpp) from [DefTruth](https://github.com/DefTruth) +* ONNXRuntime C++ Demo: [lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit/blob/main/ort/cv/rvm.cpp) and [demo](https://github.com/DefTruth/RobustVideoMatting.lite.ai.toolkit) from [DefTruth](https://github.com/DefTruth)
diff --git a/README_zh_Hans.md b/README_zh_Hans.md index 5f797a9..61f2dce 100644 --- a/README_zh_Hans.md +++ b/README_zh_Hans.md @@ -216,7 +216,13 @@ convert_video = torch.hub.load("PeterL1n/RobustVideoMatting", "converter") * 注释2：图灵架构之前的 GPU 不支持 FP16 推理，所以 GTX 1080 Ti 使用 FP32。 * 注释3：我们只测量张量吞吐量（tensor throughput）。 提供的视频转换脚本会慢得多，因为它不使用硬件视频编码/解码，也没有在并行线程上完成张量传输。如果您有兴趣在 Python 中实现硬件视频编码/解码，请参考 [PyNvCodec](https://github.com/NVIDIA/VideoProcessingFramework)。 -
+
+ +## 第三方资源 + +* NCNN C++ and Android Demo: [ncnn_Android_RobustVideoMatting](https://github.com/FeiGeChuanShu/ncnn_Android_RobustVideoMatting) from [FeiGeChuanShu](https://github.com/FeiGeChuanShu) +* ONNXRuntime C++ Demo: [lite.ai.toolkit](https://github.com/DefTruth/lite.ai.toolkit/blob/main/ort/cv/rvm.cpp) and [demo](https://github.com/DefTruth/RobustVideoMatting.lite.ai.toolkit) from [DefTruth](https://github.com/DefTruth) + ## 项目成员 * [Shanchuan Lin](https://www.linkedin.com/in/shanchuanlin/)