haotian/duan8
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
wang-xinyu 2020-12-04 22:48:32 +08:00
parent cd277360e2
commit 0b734e4818
2 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -6,10 +6,11 @@ So why don't we just skip all parsers? We just use TensorRT network definition A
I wrote this project to get familiar with tensorrt API, and also to share and learn from the community.
All the models are implemented in pytorch or mxnet first, and export a weights file xxx.wts, and then use tensorrt to load weights, define network and do inference. Some pytorch implementations can be found in my repo [Pytorchx](https://github.com/wang-xinyu/pytorchx), the remaining are from polular open-source implementations.
All the models are implemented in pytorch/mxnet/tensorflown first, and export a weights file xxx.wts, and then use tensorrt to load weights, define network and do inference. Some pytorch implementations can be found in my repo [Pytorchx](https://github.com/wang-xinyu/pytorchx), the remaining are from polular open-source implementations.
## News
- `4 Dec 2020`. DBNet dynamic input shape support by [BaofengZan](https://github.com/BaofengZan), YOLOv3 int8, PSENet(tensorflow) text detection by [upczww](https://github.com/upczww).
- `19 Nov 2020`. YOLOv3-SPP supports dynamic input shape, including a dynamic plugin.
- `17 Nov 2020`. [AlfengYuan](https://github.com/AlfengYuan) added a Dockerfile.
- `7 Nov 2020`. All models migrated to trt7 API, and clean up the master branch.
@ -76,10 +77,11 @@ Following models are implemented.
|[crnn](./crnn)| pytorch implementation from [meijieru/crnn.pytorch](https://github.com/meijieru/crnn.pytorch) |
|[ufld](./ufld)| pytorch implementation from [Ultra-Fast-Lane-Detection](https://github.com/cfzd/Ultra-Fast-Lane-Detection), ECCV2020 |
|[hrnet](./hrnet)| hrnet-image-classification, pytorch implementation from [HRNet-Image-Classification](https://github.com/HRNet/HRNet-Image-Classification) |
|[psenet](./psenet)| PSENet Text Detection, tensorflow implementation from [liuheng92/tensorflow_PSENet](https://github.com/liuheng92/tensorflow_PSENet) |
## Model Zoo
The .wts files can be downloaded from model zoo for quick evaluation. But it is recommanded to convert .wts from pytorch/mxnet model, so that you can retrain your own model.
The .wts files can be downloaded from model zoo for quick evaluation. But it is recommanded to convert .wts from pytorch/mxnet/tensorflow model, so that you can retrain your own model.
[BaiduPan](https://pan.baidu.com/s/19s6hO8esU7-TtZEXN7G3OA) pwd: uvv2

6
psenet/README.md
View File

@ -9,8 +9,9 @@ The Tensorflow implementation is [tensorflow_PSENet](https://github.com/liuheng9
- Object-Oriented Programming.
- Practice with C++ 11.
<p align="center">
<img src="https://user-images.githubusercontent.com/15235574/101176279-3868b780-3681-11eb-9ca3-7425b41fe895.jpg">
</p>
## How to Run
@ -50,4 +51,5 @@ The Tensorflow implementation is [tensorflow_PSENet](https://github.com/liuheng9
## Todo
* use `ExponentialMovingAverage` weight.
* faster preporcess and postprocess.
* faster preporcess and postprocess.