行为识别SlowFast笔记--环境配置和Demo展示

目录

前言：

1--环境配置

2--测试Demo

2-1--测试命令

2-2--测试结果

3--相关报错解决

---

前言：

        本地环境如下：

Ubuntu 20.04

Cuda 11.3

NVIDIA GeForce RTX 3060

1--环境配置

        具体请参考官方提供的文档：slowfast官方安装文档，以下为博主在本地安装的过程：

① 配置 python 环境

conda create -n slowfast python=3.8

② 配置 pytorch 环境

conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3 -c pytorch

③ 安装 fvcore

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

④ 安装simplejson

pip install simplejson

⑤ 安装PyAV

conda install av -c conda-forge

⑥ 安装iopath

pip install -U iopath

⑦ 安装psutil

pip install psutil

⑧ 安装OpenCV

pip install opencv-python

⑨ 安装tensorboard

pip install tensorboard

⑩ 安装moviepy

pip install moviepy

⑪ 安装PyTorchVideo

pip install pytorchvideo

⑫ 安装Detection

git clone https://github.com/facebookresearch/detectron2.git
python -m pip install -e detectron2

⑬ 安装FairScale

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

⑭ 安装scipy

pip isntall scipy

⑮ 安装和编译PySlowFast

git clone https://github.com/facebookresearch/slowfast
export PYTHONPATH=/home/liujinfu/Desktop/slowfast_ljf/SlowFast/slowfast:$PYTHONPATH

cd SlowFast
python setup.py build develop

2--测试Demo

2-1--测试命令

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

博主 SLOWFAST_32x2_R101_50_50.yaml 的内容如下：

TRAIN:
  ENABLE: False
  DATASET: ava
  BATCH_SIZE: 16
  EVAL_PERIOD: 1
  CHECKPOINT_PERIOD: 1
  AUTO_RESUME: True
  CHECKPOINT_FILE_PATH: /home/liujinfu/Desktop/slowfast_ljf/model/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: /home/liujinfu/Desktop/slowfast_ljf/model/ava.json
  INPUT_VIDEO: "/home/liujinfu/Desktop/slowfast_ljf/input/1.avi"
  OUTPUT_FILE: "/home/liujinfu/Desktop/slowfast_ljf/output/1.avi"
  #WEBCAM: 0
  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

需要修改的配置参数如下：

① CHECKPOINT_FILE_PATH：权重文件的路径（官方提供的权重文件下载：slowfast 已训练权重文件下载）

CHECKPOINT_FILE_PATH: /home/liujinfu/Desktop/slowfast_ljf/model/SLOWFAST_32x2_R101_50_50.pkl  #path to pretrain model

② LABEL_FILE_PATH：标签文件，博主将其构造为 ava.json 格式，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}

③ INPUT_VIDEO：输入测试视频的路径

INPUT_VIDEO: "/home/liujinfu/Desktop/slowfast_ljf/input/1.avi"

④ OUTPUT_FILE：输出测试视频的路径

OUTPUT_FILE: "/home/liujinfu/Desktop/slowfast_ljf/output/1.avi"

2-2--测试结果

        从截图可知，识别结果部分有误；

3--相关报错解决

报错 ①：error: Could not find suitable distribution for Requirement.parse('PIL');

出现在编译安装PySlowFast的过程中：python setup.py build develop；

解决方法：参考如下官方 issues，修改 setup 文件，将 PIL 修改为 Pillow；Could not find suitable distribution for Requirement.parse('PIL')

报错 ②：cannot import name 'Cal_all_gather' From 'pytorchvideo.layers.distributed';

报错的原因是未能正确安装 pytorchvideo，具体解决方法可参考如下官方 issues，从源码编译 pytorchvideo；

ImportError: cannot import name 'cat_all_gather' from 'pytorchvideo.layers.distributed'

报错 ③：no module named 'sklearn';

报错的原因是新版本不支持 sklearn，具体可见如下官方issues，解决方法是安装scikit-learn：pip install scikit-learn

INSTALL.md is not up-to-date. Here is an updated version in my SlowFast fork

报错 ④：

报错的原因是配置文件 SLOWFAST_32x2_R101_50_50.yaml 有误，具体可参考如下官方issues：

input video for demo, but got KeyError

解决方法：将配置文件有关 Tensorboard 的模块注释掉，即：

# TENSORBOARD:
  # MODEL_VIS:
    # TOPK: 2