Merge branch 'main' into lf

.readthedocs.yaml

@@ -0,0 +1,21 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+version: 2
+
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.8"
+
+sphinx:
+   configuration: conf.py
+
+# If using Sphinx, optionally build your docs in additional formats such as PDF
+formats:
+   - pdf
+
+# Optionally declare the Python requirements required to build your docs
+python:
+   install:
+   - requirements: requirements.txt

index.rst

@@ -20,6 +20,9 @@
 
    sources/pytorch/index.rst
    sources/llamafactory/index.rst
+   sources/accelerate/index.rst
+   sources/transformers/index.rst
+   sources/onnxruntime/index.rst
    sources/open_clip/index.rst
    sources/timm/index.rst
 
@@ -82,11 +85,11 @@
                 </div>
                 <div class="flex-grow"></div>
                 <div class="flex space-x-4 text-blue-600">
-                    <a href="#">官方链接</a>
+                    <a href="https://github.com/microsoft/onnxruntime">官方链接</a>
                     <span class="split">|</span>
-                    <a href="#">安装指南</a>
+                    <a href="sources/onnxruntime/install.html">安装指南</a>
                     <span class="split">|</span>
-                    <a href="#">快速上手</a>
+                    <a href="sources/onnxruntime/quick_start.html">快速上手</a>
                 </div>
             </div>
             <!-- Card 4 -->
@@ -137,7 +140,7 @@
                 </div>
                 <div class="flex-grow"></div>
                 <div class="flex space-x-4 text-blue-600">
-                    <a href="#">官方链接</a>
+                    <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui">官方链接</a>
                     <span class="split">|</span>
                     <a href="#">安装指南</a>
                     <span class="split">|</span>
@@ -156,11 +159,11 @@
                 </div>
                 <div class="flex-grow"></div>
                 <div class="flex space-x-4 text-blue-600">
-                    <a href="#">官方链接</a>
+                    <a href="https://huggingface.co/docs/transformers/index">官方链接</a>
                     <span class="split">|</span>
-                    <a href="#">安装指南</a>
+                    <a href="href="sources/transformers/install.html">安装指南</a>
                     <span class="split">|</span>
-                    <a href="#">快速上手</a>
+                    <a href="href="sources/transformers/fine-tune.html">快速上手</a>
                 </div>
             </div>
             <!-- Card 8 -->
@@ -187,16 +190,16 @@
                     <div class="img w-16 h-16 rounded-md mr-4" style="background-image: url('_static/images/huggingface.png')"></div>
                     <div>
                         <h2 class="text-lg font-semibold">Accelerate</h2>
-                        <p class="text-gray-600 desc">图像和音频生成等扩散模型工具链</p>
+                        <p class="text-gray-600 desc">适用于Pytorch的多GPUs训练工具链</p>
                     </div>
                 </div>
                 <div class="flex-grow"></div>
                 <div class="flex space-x-4 text-blue-600">
-                    <a href="#">官方链接</a>
+                    <a href="https://github.com/huggingface/accelerate">官方链接</a>
                     <span class="split">|</span>
-                    <a href="#">安装指南</a>
+                    <a href="sources/accelerate/install.html">安装指南</a>
                     <span class="split">|</span>
-                    <a href="#">快速上手</a>
+                    <a href="sources/accelerate/quick_start.html">快速上手</a>
                 </div>
             </div>
             <!-- Card 10 -->

sources/accelerate/index.rst

@@ -0,0 +1,8 @@
+Accelerate
+==============
+
+.. toctree::
+   :maxdepth: 2
+
+   install.rst
+   quick_start.rst

sources/accelerate/install.rst

@@ -0,0 +1,28 @@
+安装指南
+==============
+
+本教程面向使用 Accelerate & 昇腾的开发者，帮助完成昇腾环境下 Accelerate 的安装。
+
+Accelerate 下载安装
+--------------------
+
+.. note::
+
+    阅读本篇前，请确保已按照 :doc:`安装教程 <./install>` 准备好昇腾环境！
+    或者直接使用具备昇腾环境的镜像 `cosdt/cann:8.0.rc1-910b-ubuntu22.04 <https://hub.docker.com/layers/cosdt/cann/8.0.rc1-910b-ubuntu22.04/images/sha256-29ef8aacf6b2babd292f06f00b9190c212e7c79a947411e213135e4d41a178a9?context=explore>`_,
+    更多的版本可至 `cosdt/cann <https://hub.docker.com/r/cosdt/cann/tags>`_ 获取。
+
+启动镜像
+:::::::::::::::::
+
+.. code-block:: shell
+  
+  docker run -itd --network host -v /usr/local/dcmi:/usr/local/dcmi -v /usr/local/bin/npu-smi:/usr/local/bin/npu-smi -v /usr/local/Ascend/driver:/usr/local/Ascend/driver -v /etc/ascend_install.info:/etc/ascend_install.info --device /dev/davinci7 --device /dev/davinci_manager --device /dev/devmm_svm --device /dev/hisi_hdc --shm-size 16G --name accelerate cosdt/cann:8.0.rc1-910b-ubuntu22.04 bash
+
+安装 Accelerate 及依赖包
+::::::::::::::::::::::::::
+
+.. code-block:: shell
+
+  pip install torch==2.2.0 torch_npu==2.2.0 accelerate -i https://pypi.tuna.tsinghua.edu.cn/simple
+

sources/accelerate/quick_start.rst

@@ -0,0 +1,69 @@
+快速开始
+============
+
+.. note::
+    阅读本篇前，请确保已按照 :doc:`安装指南 <./install>` 准备好昇腾环境及 Accelerate !
+
+本教程以一个简单的 NLP 模型为例，讲述如何使用 Accelerate 在昇腾 NPU 上进行模型的训练。
+
+前置准备
+------------
+
+本篇将使用到 HuggingFace 其他工具链及 scikit-learn 库，请使用以下指令安装：
+
+.. code-block::
+
+  pip install datasets evaluate transformers scikit-learn -i https://pypi.tuna.tsinghua.edu.cn/simple
+
+本篇样例代码为 Accelrate 官方样例，需提前进行下载
+
+.. code-block::
+
+  git clone https://github.com/huggingface/accelerate.git
+
+模型训练
+------------
+
+.. code-block::
+  :linenos:
+
+  # 替换HF域名，方便国内用户进行数据及模型的下载
+  export HF_ENDPOINT=https://hf-mirror.com
+  # 进入项目目录     
+  cd accelerate/examples
+  # 模型训练
+  python nlp_example.py
+
+出现如下日志代表训练成功：
+
+::
+
+    Downloading builder script: 5.75kB [00:01, 3.69kB/s]                                                                                                  
+    tokenizer_config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████| 49.0/49.0 [00:00<00:00, 237kB/s]
+    config.json: 570B [00:00, 2.23MB/s]                                                                                                                   
+    vocab.txt: 79.5kB [00:12, 3.45kB/s]Error while downloading from https://hf-mirror.com/bert-base-cased/resolve/main/vocab.txt: HTTPSConnectionPool(host='hf-mirror.com', port=443): Read timed out.
+    Trying to resume download...
+    vocab.txt: 213kB [00:07, 15.5kB/s]]
+    vocab.txt: 91.4kB [00:32, 2.81kB/s]
+    tokenizer.json: 436kB [00:19, 22.8kB/s] 
+    Downloading readme: 35.3kB [00:01, 26.4kB/s]
+    Downloading data: 100%|█████████████████████████████████████████████████████████████████████████████████████████████| 649k/649k [00:02<00:00, 288kB/s]
+    Downloading data: 100%|██████████████████████████████████████████████████████████████████████████████████████████| 75.7k/75.7k [00:00<00:00, 77.8kB/s]
+    Downloading data: 100%|█████████████████████████████████████████████████████████████████████████████████████████████| 308k/308k [00:01<00:00, 204kB/s]
+    Generating train split: 100%|███████████████████████████████████████████████████████████████████████████| 3668/3668 [00:00<00:00, 27701.23 examples/s]
+    Generating validation split: 100%|████████████████████████████████████████████████████████████████████████| 408/408 [00:00<00:00, 73426.42 examples/s]
+    Generating test split: 100%|███████████████████████████████████████████████████████████████████████████| 1725/1725 [00:00<00:00, 246370.91 examples/s]
+    Map: 100%|███████████████████████████████████████████████████████████████████████████████████████████████| 3668/3668 [00:01<00:00, 3378.05 examples/s]
+    Map: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████| 408/408 [00:00<00:00, 3553.72 examples/s]
+    Map: 100%|███████████████████████████████████████████████████████████████████████████████████████████████| 1725/1725 [00:00<00:00, 5109.03 examples/s]
+    model.safetensors: 100%|███████████████████████████████████████████████████████████████████████████████████████████| 436M/436M [02:42<00:00, 2.68MB/s]
+    Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['classifier.bias', 'classifier.weight']
+    You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+    huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+    To disable this warning, you can either:
+      - Avoid using `tokenizers` before the fork if possible
+      - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+    You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
+    epoch 0: {'accuracy': 0.8014705882352942, 'f1': 0.8439306358381503}
+    epoch 1: {'accuracy': 0.8578431372549019, 'f1': 0.8975265017667845}
+    epoch 2: {'accuracy': 0.8700980392156863, 'f1': 0.9087779690189329}

sources/onnxruntime/index.rst

@@ -0,0 +1,8 @@
+ONNX Runtime
+============
+
+.. toctree::
+   :maxdepth: 2
+
+   install.rst
+   quick_start.rst

sources/onnxruntime/install.rst

@@ -0,0 +1,33 @@
+安装指南
+===========
+
+本教程面向使用 ONNX Runtime & Ascend NPU 的开发者，帮助完成昇腾环境下 ONNX Runtime 的安装。
+
+.. note::
+
+    阅读本篇前，请确保已按照 :doc:`安装教程 <../ascend/quick_install>` 准备好昇腾环境！
+
+ONNX Runtime 安装
+-------------------
+
+ONNX Runtime 目前提供了 源码编译 和 二进制包 两种安装方式，其中二进制包当前只支持Python。
+
+从源码安装
+^^^^^^^^^^^^
+
+.. code-block:: shell
+    :linenos:
+
+    # Default path, change it if needed.
+    source /usr/local/Ascend/ascend-toolkit/set_env.sh
+
+    ./build.sh --config <Release|Debug|RelWithDebInfo> --build_shared_lib --parallel --use_cann
+
+
+从pip安装
+^^^^^^^^^^^^
+
+.. code-block:: shell
+    :linenos:
+
+    pip3 install onnxruntime-cann

sources/onnxruntime/quick_start.rst

@@ -0,0 +1,97 @@
+快速开始
+===========
+
+.. note::
+    阅读本篇前，请确保已按照 :doc:`安装指南 <./install>` 准备好昇腾环境及 ONNX Runtime!
+
+本教程以一个简单的 resnet50 模型为例，讲述如何在 Ascend NPU上使用 ONNX Runtime 进行模型推理。
+
+环境准备
+-----------
+
+安装本教程所依赖的额外必要库。
+
+.. code-block:: shell
+  :linenos:
+
+  pip install numpy Pillow onnx
+
+模型准备
+-----------
+
+ONNX Runtime 推理需要 ONNX 格式模型作为输入，目前有以下几种主流途径获得 ONNX 模型。
+
+1. 从 `ONNX Model Zoo <https://onnx.ai/models/>`_ 中下载模型。
+2. 从 torch、TensorFlow 等框架导出 ONNX 模型。
+3. 使用转换工具，完成其他类型到 ONNX 模型的转换。
+
+本教程使用的 resnet50 模型是从 ONNX Model Zoo 中直接下载的，具体的 `下载链接 <https://github.com/onnx/models/blob/main/Computer_Vision/resnet50_Opset16_torch_hub/resnet50_Opset16.onnx>`_
+
+类别标签
+-----------
+
+类别标签用于将输出权重转换成人类可读的类别信息，具体的 `下载链接 <https://raw.githubusercontent.com/anishathalye/imagenet-simple-labels/master/imagenet-simple-labels.json>`_
+
+模型推理
+-----------
+
+.. code-block:: python
+  :linenos:
+
+  import onnxruntime as ort
+  import numpy as np
+  import onnx
+  from PIL import Image
+
+  def preprocess(image_path):
+      img = Image.open(image_path)
+      img = img.resize((224, 224))
+      img = np.array(img).astype(np.float32)
+
+      img = np.transpose(img, (2, 0, 1))
+      img = img / 255.0
+      mean = np.array([0.485, 0.456, 0.406]).reshape(3, 1, 1)
+      std = np.array([0.229, 0.224, 0.225]).reshape(3, 1, 1)
+      img = (img - mean) / std
+      img = np.expand_dims(img, axis=0)
+      return img
+
+  def inference(model_path, img):
+      options = ort.SessionOptions()
+      providers = [
+          (
+              "CANNExecutionProvider",
+              {
+                  "device_id": 0,
+                  "arena_extend_strategy": "kNextPowerOfTwo",
+                  "npu_mem_limit": 2 * 1024 * 1024 * 1024,
+                  "op_select_impl_mode": "high_performance",
+                  "optypelist_for_implmode": "Gelu",
+                  "enable_cann_graph": True
+              },
+          ),
+          "CPUExecutionProvider",
+      ]
+
+      session = ort.InferenceSession(model_path, sess_options=options, providers=providers)
+      input_name = session.get_inputs()[0].name
+      output_name = session.get_outputs()[0].name
+
+      result = session.run([output_name], {input_name: img})
+      return result
+
+  def display(classes_path, result):
+      with open(classes_path) as f:
+          labels = [line.strip() for line in f.readlines()]
+      
+      pred_idx = np.argmax(result)
+      print(f'Predicted class: {labels[pred_idx]} ({result[0][0][pred_idx]:.4f})')
+
+  if __name__ == '__main__':
+      model_path = '~/model/resnet/resnet50.onnx'
+      image_path = '~/model/resnet/cat.jpg'
+      classes_path = '~/model/resnet/imagenet_classes.txt'
+
+      img = preprocess(image_path)
+      result = inference(model_path, img)
+      display(classes_path, result)