Windows10下SlowFast环境安装和运行

文章目录[隐藏]

第一步：下载官方源码
第二步：我搭建的环境配置
第二步：安装其他包以及出现的问题
第三步：构建SlowFast
第四部：下载权重和标签
第五步：更改参数
第六步：当然是运行啦

第一步：下载官方源码

github代码链接:https://github.com/facebookresearch/SlowFast

第二步：我搭建的环境配置

电脑配置：windows10 显卡RTX3070 CPU inter i710代
我曾用了一个显卡只有4G的1650跑，直接出现显存不够错误，看样子SlowFast还是很吃显卡的
工具：pycharm

pytroch官网找的：直接搬指令
conda install pytorch1.8.0 torchvision0.9.0 torchaudio0.8.0 cudatoolkit=11.1 -c pytorch -c conda-forge
外加conda install cudnn8.2.1

第二步：安装其他包以及出现的问题

我使用的是：anaconda 新建的环境，避免和其他环境干扰。
根据INSTALL.md安装环境所依赖的包
依次按照要求安装包，我主要阐述我在安装中遇见的问题

在安装过程中：注意pytorch和cuda版本。因为官方demo使用了detectron2进行人体检测针对于detectron2有版本要求。我下载的版本要求pytorch >=1.8以上.

安装以下指令时：
pip install -U torch torchvision cython
pip install -U ‘git+https://github.com/facebookresearch/fvcore.git’ ‘git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI’ //有些不能要单引号
git clone https://github.com/facebookresearch/detectron2 detectron2_repo
#可能提取失败，多尝试几次
pip install -e detectron2_repo #编译失败，极有可能是pytorch版本和cuda版本引起的

需要注意点：
1.如果提前安装了pytorch版本，无需再执行pip install -U torch torchvision //更新pytorch版本的，我之前就在这里绕了半天
解决办法：将pip install -U torch torchvision cython 替换成 pip install -U cython

2.pip install -U ‘git+https://github.com/facebookresearch/fvcore.git’ 提取失败的话
解决办法：将git+https 更改为 git+git

3.pip install "git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI"出错
原因：国外访问链接失败，该换国内
解决办法：
linux:
pip install “git+https://gitee.com/wsyin/cocoapi.git#subdirectory=PythonAPI”
windows:
pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

第三步：构建SlowFast

在这里插入图片描述

python setup.py builddevelop 可能存在PIL一直安装不上，卡住报错误
解决办法：将PIL注释或者改为pillow

第四部：下载权重和标签

在官网链接 model zoo下：此模型为我自己选择的数据集对应模型、点击下载即可
在这里插入图片描述
新建一个标签文件xxx. json(名字随便取) 内容为：

{"bend/bow (at the waist)": 0, "crawl": 1, "crouch/kneel": 2, "dance": 3, "fall down": 4, "get up": 5, "jump/leap": 6, "lie/sleep": 7, "martial art": 8, "run/jog": 9, "sit": 10, "stand": 11, "swim": 12, "walk": 13, "answer phone": 14, "brush teeth": 15, "carry/hold (an object)": 16, "catch (an object)": 17, "chop": 18, "climb (e.g., a mountain)": 19, "clink glass": 20, "close (e.g., a door, a box)": 21, "cook": 22, "cut": 23, "dig": 24, "dress/put on clothing": 25, "drink": 26, "drive (e.g., a car, a truck)": 27, "eat": 28, "enter": 29, "exit": 30, "extract": 31, "fishing": 32, "hit (an object)": 33, "kick (an object)": 34, "lift/pick up": 35, "listen (e.g., to music)": 36, "open (e.g., a window, a car door)": 37, "paint": 38, "play board game": 39, "play musical instrument": 40, "play with pets": 41, "point to (an object)": 42, "press": 43, "pull (an object)": 44, "push (an object)": 45, "put down": 46, "read": 47, "ride (e.g., a bike, a car, a horse)": 48, "row boat": 49, "sail boat": 50, "shoot": 51, "shovel": 52, "smoke": 53, "stir": 54, "take a photo": 55, "text on/look at a cellphone": 56, "throw": 57, "touch (an object)": 58, "turn (e.g., a screwdriver)": 59, "watch (e.g., TV)": 60, "work on a computer": 61, "write": 62, "fight/hit (a person)": 63, "give/serve (an object) to (a person)": 64, "grab (a person)": 65, "hand clap": 66, "hand shake": 67, "hand wave": 68, "hug (a person)": 69, "kick (a person)": 70, "kiss (a person)": 71, "lift (a person)": 72, "listen to (a person)": 73, "play with kids": 74, "push (another person)": 75, "sing to (e.g., self, a person, a group)": 76, "take (an object) from (a person)": 77, "talk to (e.g., self, a person, a group)": 78, "watch (a person)": 79}

位置的话：你最好统一放在一个路径下，等会儿要用

第五步：更改参数

在这里插入图片描述
模型路径：就你下载那个.pkl路径

#TENSORBOARD:
#  MODEL_VIS:
#    TOPK: 2
#这个得注释，不然得报错

DEMO:
  ENABLE: True
  LABEL_FILE_PATH: F:\PythonCode\SlowFast-main\demo\AVA\ava.json
  INPUT_VIDEO: F:\PythonCode\SlowFast-main\Vinput\1.mp4
  OUTPUT_FILE: F:\PythonCode\SlowFast-main\Voutput\1.mp4
 # WEBCAM: 0  #为什么注释，看看代码，自己就知道了
  DETECTRON2_CFG: COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml
  DETECTRON2_WEIGHTS: detectron2://COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl