This commit is contained in:
66
docs/version2.x/model/hardware/install_other_devices.md
Normal file
66
docs/version2.x/model/hardware/install_other_devices.md
Normal file
@@ -0,0 +1,66 @@
|
||||
---
|
||||
comments: true
|
||||
typora-copy-images-to: images
|
||||
---
|
||||
|
||||
# 多硬件安装飞桨
|
||||
|
||||
本文档主要针对昇腾 NPU 硬件平台，介绍如何安装飞桨。
|
||||
|
||||
## 1. 昇腾 NPU 飞桨安装
|
||||
|
||||
### 1.1 环境准备
|
||||
|
||||
当前 PaddleOCR 支持昇腾 910B 芯片，昇腾驱动版本为 23.0.3。考虑到环境差异性，我们推荐使用飞桨官方提供的标准镜像完成环境准备。
|
||||
|
||||
#### 拉取镜像
|
||||
|
||||
此镜像仅为开发环境，镜像中不包含预编译的飞桨安装包，镜像中已经默认安装了昇腾算子库 CANN-8.0.RC1。
|
||||
|
||||
```bash linenums="1"
|
||||
# 适用于 X86 架构，暂时不提供 Arch64 架构镜像
|
||||
docker pull registry.baidubce.com/device/paddle-npu:cann80RC1-ubuntu20-x86_64-gcc84-py39
|
||||
```
|
||||
|
||||
#### 启动容器
|
||||
|
||||
ASCEND_RT_VISIBLE_DEVICES 指定可见的 NPU 卡号
|
||||
|
||||
```bash linenums="1"
|
||||
docker run -it --name paddle-npu-dev -v $(pwd):/work \
|
||||
--privileged --network=host --shm-size=128G -w=/work \
|
||||
-v /usr/local/Ascend/driver:/usr/local/Ascend/driver \
|
||||
-v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi \
|
||||
-v /usr/local/dcmi:/usr/local/dcmi \
|
||||
-e ASCEND_RT_VISIBLE_DEVICES="0,1,2,3,4,5,6,7" \
|
||||
registry.baidubce.com/device/paddle-npu:cann80RC1-ubuntu20-x86_64-gcc84-py39 /bin/bash
|
||||
```
|
||||
|
||||
### 1.2 安装 paddle 包
|
||||
|
||||
当前提供 Python3.9 的 wheel 安装包。如有其他 Python 版本需求，可以参考[飞桨官方文档](https://www.paddlepaddle.org.cn/install/quick)自行编译安装。
|
||||
|
||||
#### 1. 下载安装 Python3.9 的 wheel 安装包
|
||||
|
||||
```bash linenums="1"
|
||||
# 注意需要先安装飞桨 cpu 版本
|
||||
pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddle-device/npu/paddlepaddle-0.0.0-cp39-cp39-linux_x86_64.whl
|
||||
pip install https://paddle-model-ecology.bj.bcebos.com/paddlex/whl/paddle-device/npu/paddle_custom_npu-0.0.0-cp39-cp39-linux_x86_64.whl
|
||||
```
|
||||
|
||||
#### 2. 验证安装包
|
||||
|
||||
安装完成之后，运行如下命令。
|
||||
|
||||
```bash linenums="1"
|
||||
python -c "import paddle; paddle.utils.run_check()"
|
||||
```
|
||||
|
||||
预期得到如下输出结果
|
||||
|
||||
```bash linenums="1"
|
||||
Running verify PaddlePaddle program ...
|
||||
PaddlePaddle works well on 1 npu.
|
||||
PaddlePaddle works well on 8 npus.
|
||||
PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.
|
||||
```
|
||||
12
docs/version2.x/model/hardware/supported_models.md
Normal file
12
docs/version2.x/model/hardware/supported_models.md
Normal file
@@ -0,0 +1,12 @@
|
||||
---
|
||||
comments: true
|
||||
typora-copy-images-to: images
|
||||
---
|
||||
|
||||
# PaddleOCR模型列表
|
||||
|
||||
*多硬件安装方式请参考[多硬件安装文档](./install_other_devices.md)*
|
||||
|
||||
| 模型名称 | 昇腾NPU |
|
||||
| ---------------- | -------- |
|
||||
| PP-OCRv4 | √ |
|
||||
25
docs/version2.x/model/index.md
Normal file
25
docs/version2.x/model/index.md
Normal file
@@ -0,0 +1,25 @@
|
||||
---
|
||||
comments: true
|
||||
hide:
|
||||
- toc
|
||||
---
|
||||
|
||||
## PP-OCR 系列模型列表（更新中）
|
||||
|
||||
| 模型简介 | 模型名称 | 推荐场景 | 检测模型| 方向分类器 | 识别模型|
|
||||
| ----- | -------------- | --------------- | ------- | ------- | ---------- |
|
||||
| 中英文超轻量 PP-OCRv4 模型（15.8M） | PP-OCRv4_mobile_det | 移动端&服务器端 | [推理模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_det_infer.tar) / [训练模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv4_mobile_det_pretrained.pdparams) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_mobile_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_train.tar) |
|
||||
| 中英文超轻量 PP-OCRv3 模型（16.2M） | PP-OCRv3_mobile_det | 移动端&服务器端 | [推理模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_det_infer.tar) / [训练模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-OCRv3_mobile_det_pretrained.pdparams ) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv3_mobile_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
|
||||
| 英文超轻量 PP-OCRv3 模型（13.4M） | en_PP-OCRv3_xx | 移动端&服务器端 | [推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_distill_train.tar) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | [推理模型](https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/en_PP-OCRv3_mobile_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
|
||||
|
||||
- 超轻量 OCR 系列更多模型下载（包括多语言），可以参考[PP-OCR 系列模型下载](../ppocr/model_list.md)，文档分析相关模型参考[PP-Structure 系列模型下载](../ppstructure/models_list.md)
|
||||
|
||||
### PaddleOCR 场景应用模型
|
||||
|
||||
| 行业 | 类别 | 亮点| 文档说明| 模型下载 |
|
||||
| ---- | ---- | -------- | ---- | ----- |
|
||||
| 制造 | 数码管识别 | 数码管数据合成、漏识别调优 | [光功率计数码管字符识别](../applications/光功率计数码管字符识别.md) | [下载链接](../applications/overview.md) |
|
||||
| 金融 | 通用表单识别 | 多模态通用表单结构化提取 | [多模态表单识别](../applications/多模态表单识别.md) | [下载链接](../applications/overview.md) |
|
||||
| 交通 | 车牌识别 | 多角度图像处理、轻量模型、端侧部署 | [轻量级车牌识别](../applications/轻量级车牌识别.md) | [下载链接](../applications/overview.md) |
|
||||
|
||||
- 更多制造、金融、交通行业的主要 OCR 垂类应用模型（如电表、液晶屏、高精度 SVTR 模型等），可参考[场景应用模型下载](../applications/overview.md)
|
||||
Reference in New Issue
Block a user