start working on object-detection

.gitignore

@@ -2,3 +2,4 @@
 /runs/
 .vim/
 .ipynb_checkpoints
+/models/

TorchObjectDetection.ipynb

@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "本教程将会在预训练模型 [Mask R_CNN](https://arxiv.org/abs/1703.06870) 上针对  [Penn-Fudan Database for Pedestrian Detection and Segmentation](https://www.cis.upenn.edu/~jshi/ped_html/)数据进行调优。这个数据集有170张图片，345个行人，通过本教程可学习到如何使用 torchvision 的新特性来训练针对特定数据集的分割模型。\n",
+    "\n",
+    "\n",
+    "# 定义数据集\n",
+    "\n",
+    "按照训练物体检测，分割和人体关键点模型的参考脚本，可以很方便地支持添加新的自定义数据集。新的数据集必须继承 `torch.utils.data.Dataset` 类，同时实现 `__len__` 和 `__getitem__` 方法\n",
+    "\n",
+    "唯一需要注意的话，我们要坟 `__getitem__` 返回的格式如下：\n",
+    "\n",
+    "* image: 一个 `PILImage` 图像对象，其尺寸为 `(H,W)`\n",
+    "* target: 一个 `dict` 对象，含有以下的键：\n",
+    "    * `boxes[FloatTensor[N, 4)`: 含有 `N` 个 bounding box 的数组，其元素为4个，格式为`[x0, y0, x1, y1]`\n",
+    "    * `labels (Int64Tensor[N])`: 每个 bounding box 的标签。 `0` 表示背景\n",
+    "    * `image_id (Int64Tensor[1])`: 图像id，必须在整个数据集中唯一。\n",
+    "    * `area (Tensor[N])`: bounding box 的面积。用以 Coco metric 评估，分离大小不同的boxes\n",
+    "    * `iscrowd (UintTensor[N])': 该值为True时，将不会被用以评估\n",
+    "    * 可选 `masks (UInt8Tensor[N, H, W])`: 每个物体的分离蒙板\n",
+    "    * 可选 `keypoints (FloatTensor[N, K, 3])`: 对于 `N` 个物体，含有 `K` 个关键点。关键点的格式为`[x, y, visibility]`。`visibility=0` 表示关键点不可见。\n",
+    "\n",
+    "\n",
+    "data source: https://www.cis.upenn.edu/~jshi/ped_html/PennFudanPed.zip"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}