fix typos

SangbumChoi · Mar 3, 2023 · 8a49083 · 8a49083
1 parent 15d866d
commit 8a49083
Show file tree

Hide file tree

Showing 4 changed files with 12 additions and 16 deletions.
diff --git a/README.md b/README.md
@@ -25,7 +25,7 @@ Implementation of paper:
 
 
 ## What's New
-- [2023.3.2] Updates [base models](configs/base/README.md) to version 0.3.
+- [2023.03.02] Update [base models](configs/base/README.md) to version 3.0.
 - [2023.01.06] Release P6 models and enhance the performance of P5 models. ⭐️ [Benchmark](#Benchmark)
     - Renew the neck of the detector with a BiC module and SimCSPSPPF Block.
     - Propose an anchor-aided training (AAT) strategy.

diff --git a/README_cn.md b/README_cn.md
@@ -16,7 +16,7 @@
 
 
 ## 更新日志
-- [2023.3.2] 更新 [基础版模型](configs/base/READM_cn.md) 到 0.3 版本。
+- [2023.03.02] 更新 [基础版模型](configs/base/READM_cn.md) 到 3.0 版本
 - [2023.01.06] 发布大分辨率 P6 模型以及对 P5 模型做了全面的升级 ⭐️ [模型指标](#模型指标)
     - 添加 BiC 模块 和 SimCSPSPPF 模块以增强检测网络颈部的表征能力。
     - 提出一个锚点辅助训练 (AAT) 策略。

diff --git a/configs/base/README.md b/configs/base/README.md
@@ -9,20 +9,18 @@ English | [简体中文](./README_cn.md)
 - Apply CSP (1/2 channel dim) blocks in the network structure, except for Nano base model.
 
 Advantage:
-- Adopt a unified network structure and configuration, and the accuracy loss of the PTQ 8-bit quantization model is negligible, about 0.4%.
+- Adopt a unified network structure and configuration, and the accuracy loss of the PTQ 8-bit quantization model is negligible.
 - Suitable for users who are just getting started or who need to apply, optimize and deploy an 8-bit quantization model quickly and frequently.
 
-Shortcoming:
-- The accuracy on COCO is slightly lower than the v2.0 released models.
 
 ### Performance
 
 | Model                                                         | Size | mAP<sup>val<br/>0.5:0.95 | Speed<sup>T4<br/>TRT FP16 b1 <br/>(FPS) | Speed<sup>T4<br/>TRT FP16 b32 <br/>(FPS) | Speed<sup>T4<br/>TRT INT8 b1 <br/>(FPS) | Speed<sup>T4<br/>TRT INT8 b32 <br/>(FPS) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
 | :--------------------------------------------------------------------------------------------- | --- | ----------------- | ----- | ---- | ---- | ---- | ----- | ------ |
-| [**YOLOv6-N-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6n_base.pt) | 640 | 36.6<sup>distill  | 727   | 1302 | 814  | 1805 | 4.65  | 11.46  |
-| [**YOLOv6-S-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6s_base.pt) | 640 | 45.3<sup>distill  | 346   | 525  | 487  | 908  | 13.14 | 30.6   |
-| [**YOLOv6-M-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6m_base.pt) | 640 | 49.4<sup>distill  | 179   | 245  | 284  | 439  | 28.33 | 72.30  |
-| [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6l_base.pt) | 640 | 51.1<sup>distill  | 116   | 157  | 196  | 288  | 59.61 | 150.89 |
+| [**YOLOv6-N-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n_base.pt) | 640 | 36.6<sup>distill  | 727   | 1302 | 814  | 1805 | 4.65  | 11.46  |
+| [**YOLOv6-S-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s_base.pt) | 640 | 45.3<sup>distill  | 346   | 525  | 487  | 908  | 13.14 | 30.6   |
+| [**YOLOv6-M-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m_base.pt) | 640 | 49.4<sup>distill  | 179   | 245  | 284  | 439  | 28.33 | 72.30  |
+| [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l_base.pt) | 640 | 51.1<sup>distill  | 116   | 157  | 196  | 288  | 59.61 | 150.89 |
 
 - Speed is tested with TensorRT 8.2.4.2 on T4.
 - The processes of model training, evaluation, and inference are the same as the original ones. For details, please refer to [this README](https://github.com/meituan/YOLOv6#quick-start).
diff --git a/configs/base/README_cn.md b/configs/base/README_cn.md
@@ -9,19 +9,17 @@
 - 网络结构均采用CSP (1/2通道) block，Nano网络除外。
 
 优势：
-- 采用统一的网络结构和配置，且 PTQ 8位量化模型精度损失(约0.4%)较小，适合刚入门或有快速迭代部署8位量化模型需求的用户。
+- 采用统一的网络结构和配置，且 PTQ 8位量化模型精度损失较小，适合刚入门或有快速迭代部署8位量化模型需求的用户。
 
-不足：
-- COCO上精度对比2.0版本发布模型稍低。
 
 ### 模型指标
 
 | 模型 | 尺寸 | mAP<sup>val<br/>0.5:0.95 | 速度<sup>T4<br/>TRT FP16 b1 <br/>(FPS) | 速度<sup>T4<br/>TRT FP16 b32 <br/>(FPS) | 速度<sup>T4<br/>TRT INT8 b1 <br/>(FPS) | 速度<sup>T4<br/>TRT INT8 b32 <br/>(FPS) | Params<br/><sup> (M) | FLOPs<br/><sup> (G) |
 | :--------------------------------------------------------------------------------------------- | --- | ----------------- | ----- | ---- | ---- | ---- | ----- | ------ |
-| [**YOLOv6-N-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6n_base.pt) | 640 | 36.6<sup>distill  | 727   | 1302 | 814  | 1805 | 4.65  | 11.46  |
-| [**YOLOv6-S-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6s_base.pt) | 640 | 45.3<sup>distill  | 346   | 525  | 487  | 908  | 13.14 | 30.6   |
-| [**YOLOv6-M-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6m_base.pt) | 640 | 49.4<sup>distill  | 179   | 245  | 284  | 439  | 28.33 | 72.30  |
-| [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.2.1/yolov6l_base.pt) | 640 | 51.1<sup>distill  | 116   | 157  | 196  | 288  | 59.61 | 150.89 |
+| [**YOLOv6-N-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6n_base.pt) | 640 | 36.6<sup>distill  | 727   | 1302 | 814  | 1805 | 4.65  | 11.46  |
+| [**YOLOv6-S-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6s_base.pt) | 640 | 45.3<sup>distill  | 346   | 525  | 487  | 908  | 13.14 | 30.6   |
+| [**YOLOv6-M-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6m_base.pt) | 640 | 49.4<sup>distill  | 179   | 245  | 284  | 439  | 28.33 | 72.30  |
+| [**YOLOv6-L-base**](https://github.com/meituan/YOLOv6/releases/download/0.3.0/yolov6l_base.pt) | 640 | 51.1<sup>distill  | 116   | 157  | 196  | 288  | 59.61 | 150.89 |
 
 - 速度是在 T4 上测试的，TensorRT 版本为 8.4.2.4；
 - 模型训练、评估、推理流程与原来保持一致，具体可参考 [首页 README 文档](https://github.com/meituan/YOLOv6/blob/main/README_cn.md#%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B)。