在AutoDL平台上复现SlowFast的demo

最新推荐文章于 2024-01-04 03:39:09 发布

半城喧嚣、半城空

最新推荐文章于 2024-01-04 03:39:09 发布

阅读量1.4k

点赞数 11

分类专栏： python相关文章标签： python

本文链接：https://blog.csdn.net/qq_51223728/article/details/127915758

版权

python相关专栏收录该内容

3 篇文章 0 订阅

订阅专栏

一、前言

由于本业余人士水平有限，在复现过程中经历了种种报错，最终皇天不负有心人，我成功把demo跑出来了。源码地址：https://github.com/facebookresearch/SlowFast，但是由于官网一直有人维护，git下来的版本是最新代码，复现会出现各种问题。所以选择一个较老版本：参考https://blog.csdn.net/weixin_48841074/article/details/116807805

git clone https://gitee.com/qiang_sun/SlowFast.git

二、复现步骤

在AutoDL平台租用GPU（RTX3090*1，显存24GB，CPU内存80GB，系统盘25GB）。框架（Pytorch 1.8.1，Python 3.8(Ubuntu18.04)，Cuda 11.1)。（RTX3090算力为8.6，cuda版本至少为11.x）**注意：**JupyterLab的工作目录为/root目录，而非/系统根目录。

打开终端，安装依赖：

更新pip
```
pip install --upgrade pip
```

安装fvcore

# 在AutoDL平台上可以参考帮助文档使用学术资源加速

pip install 'git+https://github.com/facebookresearch/fvcore'

关闭加速
```
unset http_proxy && unset https_proxy
```

# 在实例AutoPanel手动切换pip软件源(首选阿里源,若慢则重选清华源)

安装simplejson
```
pip install simplejson
```
安装PyAv
```
pip install av==8.0.3
```
安装iopath
```
pip install -U iopath
```
安装psutil
```
pip install psutil
```
安装opencv-python
```
pip install opencv-python
```
安装tensorboard
```
pip install tensorboard
```
安装cython
```
pip install cython
```
下载detectron2，这里与官网方式不同。(要求pytorch>=1.8)参考 https://github.com/facebookresearch/detectron2/releases
```
# 在AutoDL平台上可以参考帮助文档使用学术资源加速
```
```
git clone https://github.com/facebookresearch/detectron2
```
关闭加速
```
unset http_proxy && unset https_proxy
```
安装detectron2
```
pip install -e detectron2
```

下载SlowFsast

git clone https://gitee.com/qiang_sun/SlowFast.git

导入路径，路径如下图所示，修改成你自己的路径即可
```
export PYTHONPATH=/root/SlowFast/slowfast:$PYTHONPATH
```
安装pandas和scikit-learn，有可能上面的过程引起了删除，我没去找具体原因
```
pip install pandas
pip install scikit-learn
```
进入SlowFast目录
```
cd SlowFast
```
编译，可以干点别的事等着，非常慢
```
python setup.py build develop
```

在这里插入图片描述

下载预训练模型：下载页面

如图所示的权重文件：link，放到/root/SlowFast/configs/AVA/c2目录下

在这里插入图片描述
4. 修改部分代码

在/SlowFast/demo/AVA目录下新建ava.json，文件内容如下：

{"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}

修改/SlowFast/demo/AVA/SLOWFAST_32x2_R101_50_50.yaml，内容改为如下：

TRAIN:
  ENABLE: False
  DATASET: ava
  BATCH_SIZE: 16
  EVAL_PERIOD: 1
  CHECKPOINT_PERIOD: 1
  AUTO_RESUME: True
  CHECKPOINT_FILE_PATH: "/root/SlowFast/configs/AVA/c2/SLOWFAST_32x2_R101_50_50.pkl"  #path to pretrain model
  CHECKPOINT_TYPE: pytorch
DATA:
  NUM_FRAMES: 32
  SAMPLING_RATE: 2
  TRAIN_JITTER_SCALES: [256, 320]
  TRAIN_CROP_SIZE: 224
  TEST_CROP_SIZE: 256
  INPUT_CHANNEL_NUM: [3, 3]
DETECTION:
  ENABLE: True
  ALIGNED: False
AVA:
  BGR: False
  DETECTION_SCORE_THRESH: 0.8
  TEST_PREDICT_BOX_LISTS: ["person_box_67091280_iou90/ava_detection_val_boxes_and_labels.csv"]
SLOWFAST:
  ALPHA: 4
  BETA_INV: 8
  FUSION_CONV_CHANNEL_RATIO: 2
  FUSION_KERNEL_SZ: 5
RESNET:
  ZERO_INIT_FINAL_BN: True
  WIDTH_PER_GROUP: 64
  NUM_GROUPS: 1
  DEPTH: 101
  TRANS_FUNC: bottleneck_transform
  STRIDE_1X1: False
  NUM_BLOCK_TEMP_KERNEL: [[3, 3], [4, 4], [6, 6], [3, 3]]
  SPATIAL_DILATIONS: [[1, 1], [1, 1], [1, 1], [2, 2]]
  SPATIAL_STRIDES: [[1, 1], [2, 2], [2, 2], [1, 1]]
NONLOCAL:
  LOCATION: [[[], []], [[], []], [[6, 13, 20], []], [[], []]]
  GROUP: [[1, 1], [1, 1], [1, 1], [1, 1]]
  INSTANTIATION: dot_product
  POOL: [[[2, 2, 2], [2, 2, 2]], [[2, 2, 2], [2, 2, 2]], [[2, 2, 2], [2, 2, 2]], [[2, 2, 2], [2, 2, 2]]]
BN:
  USE_PRECISE_STATS: False
  NUM_BATCHES_PRECISE: 200
SOLVER:
  MOMENTUM: 0.9
  WEIGHT_DECAY: 1e-7
  OPTIMIZING_METHOD: sgd
MODEL:
  NUM_CLASSES: 80
  ARCH: slowfast
  MODEL_NAME: SlowFast
  LOSS_FUNC: bce
  DROPOUT_RATE: 0.5
  HEAD_ACT: sigmoid
TEST:
  ENABLE: False
  DATASET: ava
  BATCH_SIZE: 8
DATA_LOADER:
  NUM_WORKERS: 2
  PIN_MEMORY: True

NUM_GPUS: 1
NUM_SHARDS: 1
RNG_SEED: 0
OUTPUT_DIR: .

#TENSORBOARD:
#  MODEL_VIS:
#    TOPK: 2
DEMO:
  ENABLE: True
  LABEL_FILE_PATH: "/root/SlowFast/demo/AVA/ava.json"
  #WEBCAM: 0
  #下面两个文件夹是自己建立的(VINPUT和VOUTPUT)
  INPUT_VIDEO: "/root/SlowFast/VINPUT/1.mp4" #自己上传一段测试视频
  OUTPUT_FILE: "/root/SlowFast/VOUTPUT/2.mp4"

  DETECTRON2_CFG: "COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml"
  DETECTRON2_WEIGHTS: https://dl.fbaipublicfiles.com/detectron2/COCO-Detection/faster_rcnn_R_50_FPN_3x/137849458/model_final_280758.pkl

运行代码

# 先进入到SlowFast文件夹

python tools/run_net.py --cfg demo/AVA/SLOWFAST_32x2_R101_50_50.yaml

运行效果：
在这里插入图片描述

三、遇到的问题

1.安装最新detectron2（V0.6）需要保证pytorch>=1.8
2.安装PyAv要指定版本av==8.0.3

半城喧嚣、半城空

关注

11
点赞
踩
29

收藏

觉得还不错? 一键收藏
7
评论
在AutoDL平台上复现SlowFast的demo

一、前言由于本业余人士水平有限，在复现过程中经历了种种报错，最终皇天不负有心人，我成功把demo跑出来了。源码地址：https://github.com/facebookresearch/SlowFast，但是由于官网一直有人维护，git下来的版本是最新代码，复现会出现各种问题。所以选择一个较老版本：参考https://blog.csdn.net/weixin_48841074/article/details/116807805git clone https://gitee.com/qiang_su
复制链接

扫一扫