From 72096bacef12ff369ecb176c17e23caa1638cf7e Mon Sep 17 00:00:00 2001 From: Yuto Nakamura Date: Wed, 25 Oct 2023 09:49:43 +0000 Subject: [PATCH] add download link --- README.md | 11 +++++------ docs/README_ja.md | 10 +++++----- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 2c5ce6d..f46a620 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ For more information about the development, please visit [https://zenn.dev/turin 3. Download the pretrained weights. ```bash - wget https://github.com/... models/ + wget https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_s.pth -P models ``` ## Demo @@ -60,11 +60,10 @@ python tools/export_onnx.py --output-name openlenda_s.onnx\ AP and AR are evaluated on the private validation set. The results are shown below. | Model | size | AP50 | AR50 | Download | |:---:|:---:|:---:|:---:|:---:| -| OpenLenda-nano | 416x416 | 0.941 |0.830 | | -| OpenLenda-tiny | 416x416 | 0.944 | 0.807 | | -| OpenLenda-s | 640x640 | 0.964 | 0.946 | | -| OpenLenda-x | 640x640 | 0.950 | 0.961 | | - +| OpenLenda-nano | 416x416 | 0.941 |0.830 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_nano.pth) | +| OpenLenda-tiny | 416x416 | 0.944 | 0.807 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_tiny.pth) | +| OpenLenda-s | 640x640 | 0.964 | 0.946 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_s.pth) | +| OpenLenda-x | 640x640 | 0.950 | 0.961 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_x.pth)| # 📚Documentation Please see YOLOX's [README](https://github.com/Megvii-BaseDetection/YOLOX/blob/main/README.md) or [docs](docs) (almost same as YOLOX's). diff --git a/docs/README_ja.md b/docs/README_ja.md index 43b1df2..e098c00 100644 --- a/docs/README_ja.md +++ b/docs/README_ja.md @@ -37,7 +37,7 @@ 3. 学習済みの重みをダウンロードします。 ```bash - wget https://github.com/... models/ + https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_s.pth ``` ## Demo @@ -60,10 +60,10 @@ python tools/export_onnx.py --output-name openlenda_s.onnx\ APやARは非公開の検証セットで評価されています。結果は以下の通りです。(score threshold: 0.45) | Model | size | AP50 | AR50 | Download | |:---:|:---:|:---:|:---:|:---:| -| OpenLenda-nano | 416x416 | 0.941 |0.830 | | -| OpenLenda-tiny | 416x416 | 0.944 | 0.807 | | -| OpenLenda-s | 640x640 | 0.964 | 0.946 | | -| OpenLenda-x | 640x640 | 0.950 | 0.961 | | +| OpenLenda-nano | 416x416 | 0.941 |0.830 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_nano.pth) | +| OpenLenda-tiny | 416x416 | 0.944 | 0.807 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_tiny.pth) | +| OpenLenda-s | 640x640 | 0.964 | 0.946 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_s.pth) | +| OpenLenda-x | 640x640 | 0.950 | 0.961 | [link](https://github.com/uringmotors/openlenda/releases/latest/download/openlenda_x.pth)| # 📚Documentation