PaddleX/paddlex/repo_apis/PaddleVideo_api/configs/PP-TSM-R50_8frames_uniform.yaml

Global:
  checkpoints: null
  pretrained_model: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_pretrained_model/PP-TSM-R50_8frames_uniform_pretrained.pdparams
  output_dir: ./output/
  device: gpu
  use_visualdl: False
  save_inference_dir: ./inference
  # training model under @to_static
  to_static: False
  algorithm: PP-TSM-R50_8frames_uniform

MODEL: #MODEL field
    framework: "Recognizer2D" #Mandatory, indicate the type of network, associate to the 'paddlevideo/modeling/framework/' .
    backbone: #Mandatory, indicate the type of backbone, associate to the 'paddlevideo/modeling/backbones/' .
        name: "ResNetTweaksTSM" #Mandatory, The name of backbone.
        pretrained: null
        depth: 50 #Optional, the depth of backbone architecture.
    head:
        name: "ppTSMHead" #Mandatory, indicate the type of head, associate to the 'paddlevideo/modeling/heads'
        num_classes: 400 #Optional, the number of classes to be classified.
        in_channels: 2048 #input channel of the extracted feature.
        drop_ratio: 0.5 #the ratio of dropout
        std: 0.01 #std value in params initialization
        ls_eps: 0.1 # label smooth factor

DATASET: #DATASET field
    batch_size: 16  #Mandatory, bacth size
    num_workers: 4 #Mandatory, the number of subprocess on each GPU.
    # test_batch_size: 1
    train:
        format: "VideoDataset" #Mandatory, indicate the type of dataset, associate to the 'paddlevidel/loader/dateset'
        data_prefix: "K400_dataset/K400/videos"  #Mandatory, train data root path
        file_path: "K400_dataset/K400/train.txt" #Mandatory, train data index file path
    valid:
        format: "VideoDataset" #Mandatory, indicate the type of dataset, associate to the 'paddlevidel/loader/dateset'
        data_prefix: "K400_dataset/K400/videos"  #Mandatory, train data root path
        file_path: "K400_dataset/K400/val.txt" #Mandatory, valid data index file path
    test:
        format: "VideoDataset" #Mandatory, indicate the type of dataset, associate to the 'paddlevidel/loader/dateset'
        data_prefix: "K400_dataset/K400/videos"  #Mandatory, train data root path
        file_path: "K400_dataset/K400/val.txt" #Mandatory, valid data index file path

PIPELINE: #PIPELINE field
    train: #Mandotary, indicate the pipeline to deal with the training data, associate to the 'paddlevideo/loader/pipelines/'
        decode:
            name: "VideoDecoder"
            backend: "decord"
        sample:
            name: "Sampler"
            num_seg: 8
            seg_len: 1
            valid_mode: False
        transform: #Mandotary, image transform operator
            - Scale:
                short_size: 256
            - MultiScaleCrop:
                target_size: 256
            - RandomCrop:
                target_size: 224
            - RandomFlip:
            - Image2Array:
            - Normalization:
                mean: [0.485, 0.456, 0.406]
                std: [0.229, 0.224, 0.225]
    valid: #Mandatory, indicate the pipeline to deal with the validating data. associate to the 'paddlevideo/loader/pipelines/'
        decode:
            name: "VideoDecoder"
            backend: "decord"
        sample:
            name: "Sampler"
            num_seg: 8
            seg_len: 1
            valid_mode: True
        transform:
            - Scale:
                short_size: 256
            - CenterCrop:
                target_size: 224
            - Image2Array:
            - Normalization:
                mean: [0.485, 0.456, 0.406]
                std: [0.229, 0.224, 0.225]
    test:  #Mandatory, indicate the pipeline to deal with the validating data. associate to the 'paddlevideo/loader/pipelines/'
        decode:
            name: "VideoDecoder"
            backend: "decord"
        sample:
            name: "Sampler"
            num_seg: 8
            seg_len: 1
            valid_mode: True
        transform:
            - Scale:
                short_size: 256
            - CenterCrop:
                target_size: 224
            - Image2Array:
            - Normalization:
                mean: [0.485, 0.456, 0.406]
                std: [0.229, 0.224, 0.225]

OPTIMIZER: #OPTIMIZER field
  name: 'Momentum'
  momentum: 0.9
  learning_rate:
    iter_step: True
    name: 'CustomWarmupCosineDecay'
    max_epoch: 80
    warmup_epochs: 10
    warmup_start_lr: 0.005
    cosine_base_lr: 0.01
  weight_decay:
    name: 'L2'
    value: 1e-4
  use_nesterov: True

MIX:
    name: "Mixup"
    alpha: 0.2

PRECISEBN:
  preciseBN_interval: 5     # epoch interval to do preciseBN, default 1.
  num_iters_preciseBN: 200  # how many batches used to do preciseBN, default 200.


METRIC:
    name: 'CenterCropMetric'

INFERENCE:
    name: 'ppTSM_Inference_helper'
    num_seg: 8
    target_size: 224

Infer:
    transforms:
        - ReadVideo:
            num_seg: 8
            sample_type: 'uniform'
        - Scale:
            short_size: 256
        - CenterCrop:
            target_size: 224
        - Image2Array:
            data_format: 'tchw'
        - NormalizeVideo:
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225] 
    PostProcess:
        name: Topk
        topk: 1
        class_id_map_file: data/k400/Kinetics-400_label_list.txt     

model_name: "ppTSM"
log_interval: 10 #Optional, the interval of logger, default:10
epochs: 80 #Mandatory, total epoch
log_level: "INFO" #Optional, the logger level. default: "INFO"