Skip to content

Commit

Permalink
[Update] docs (#1098)
Browse files Browse the repository at this point in the history
  • Loading branch information
megemini authored Nov 21, 2024
1 parent c9d73bc commit 97c38db
Show file tree
Hide file tree
Showing 5 changed files with 14 additions and 9 deletions.
14 changes: 8 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -47,13 +47,15 @@ X2Paddle是飞桨生态下的模型转换工具,致力于帮助其它深度学
## 安装

### 环境依赖
- python >= 3.5
- paddlepaddle >= 2.2.2 (官方验证到2.4.2)
- tensorflow == 1.14 (如需转换TensorFlow模型)
- onnx >= 1.6.0 (如需转换ONNX模型)
- torch >= 1.5.0 (如需转换PyTorch模型)
- python >= 3.8
- paddlepaddle >= 2.2.2 (官方验证到 `3.0.0beta1`)
- tensorflow == 1.14 (如需转换TensorFlow模型。其中 `test_benchmark` 模型已在 `2.16.1` 测试通过)
- onnx >= 1.6.0 (如需转换ONNX模型,其中 `test_benchmark` 模型已在 `1.17.0` 测试通过)
- torch >= 1.5.0 (如需转换PyTorch模型,其中 `test_benchmark` 模型已在 `2.4.1` 测试通过)
- paddlelite >= 2.9.0 (如需一键转换成Paddle-Lite支持格式,推荐最新版本)

> 说明:以上测试通过的版本,不代表 X2Paddle 支持相应版本中的所有算子,仅表示可在此环境中使用。具体支持的算子请详见 [支持列表](./docs/inference_model_convertor/op_list.md)
### pip安装(推荐)

如需使用稳定版本,可通过pip方式安装X2Paddle:
Expand Down Expand Up @@ -157,5 +159,5 @@ x2paddle --framework=caffe --prototxt=deploy.prototxt --weight=deploy.caffemodel

我们非常欢迎您为X2Paddle贡献代码或者提供使用建议:
- 如果您可以修复某个issue或者增加一个新功能,欢迎给我们提交Pull Requests
- 可以使用[开发镜像](./docker)[paddlepaddle/x2paddle:latest-dev-cuda11.2-cudnn8-gcc82](https://hub.docker.com/r/paddlepaddle/x2paddle/tags),国内镜像下载地址:https://x2paddle.bj.bcebos.com/Docker/latest-dev-cuda11.2-cudnn8-gcc82.tar
- 可以使用[开发镜像](./docker)[paddlepaddle/x2paddle:latest-dev-cuda11.8-cudnn8.6-trt8.5-gcc82](https://hub.docker.com/r/paddlepaddle/x2paddle/tags)
- 如果有PyTorch训练项目转换需求欢迎随时提issue
3 changes: 2 additions & 1 deletion docs/inference_model_convertor/op_list.md
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,8 @@ Aten:
| 133 | aten::rsqrt | 134 | aten::replication\_pad1d | 135 | aten::full | 136 | aten::group\_norm |
| 137 | aten::argmax | 138 | aten::copy | 139 | aten::upsample\_trilinear3d | 140 | aten::clone |
| 137 | aten::argmax | 138 | aten::copy | 139 | aten::upsample\_trilinear3d | 140 | aten::\_convolution\_mode |
| 141 | aten::rand | 142 | aten::randn | 143 | aten::clone | | |
| 141 | aten::rand | 142 | aten::randn | 143 | aten::clone | 144 | aten::pad |
| 145 | aten::list | 146 | aten::linalg\_vector\_norm | 147 | aten::unsafe\_chunk | | |

Prim:
| 序号 | OP | 序号 | OP | 序号 | OP | 序号 | OP |
Expand Down
2 changes: 2 additions & 0 deletions docs/introduction/x2paddle_model_zoo.md
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,8 @@
| SOLAR |[code](https://github.com/tonyngjichun/SOLAR) |只支持trace模式|
| YOLOX |[code](https://github.com/Megvii-BaseDetection/YOLOX) |只支持trace模式|
| MockingBird |[code](https://github.com/babysor/MockingBird) |只支持trace模式|
| gpt2 |[code](https://hf-mirror.com/openai-community/gpt2/tree/main) |只支持trace模式|
| mt5_small |[code](https://hf-mirror.com/google/mt5-small/tree/main) |只支持trace模式|


## PyTorch训练项目
Expand Down
2 changes: 1 addition & 1 deletion test_autoscan/start_autoscan_torch.sh
Original file line number Diff line number Diff line change
Expand Up @@ -17,4 +17,4 @@ set -x
#
# bash run_autoscan_torch.sh ${torch_version}
#done
bash run_autoscan_torch.sh 1.7.0
bash run_autoscan_torch.sh 2.4.1
2 changes: 1 addition & 1 deletion x2paddle/__init__.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
__version__ = "1.4.1"
__version__ = "1.6.0"

from .core.program import PaddleGraph

Expand Down

0 comments on commit 97c38db

Please sign in to comment.