lingyunwu14 / stft Goto Github PK

Spatial-Temporal Feature Transformation for Video Object Detection, MICCAI2021

License: Other

Python 81.57% C 1.29% C++ 2.24% Cuda 14.90%

stft's Issues

Training and testing on VID dataset

Thank you for sharing the codes! There exist some codes for the VID dataset in ./data/datasets/vid.py and stft_core/config/path_catalog.py. Have you trained and tested the model on the VID dataset? How it performs? It seems to perform so badly when I use the config:

MODEL:
  VID:
    ENABLE: True
    METHOD: "stft"
    STFT:
      MIN_OFFSET: -9
      MAX_OFFSET: 9
      TRAIN_REF_NUM: 2
      TEST_REF_NUM: 10
  META_ARCHITECTURE: "GeneralizedRCNNSTFT"
  WEIGHT: "catalog://ImageNetPretrained/MSRA/R-50"
  RPN_ONLY: True
  FCOS_ON: True
  STFT_ON: True
  BACKBONE:
    CONV_BODY: "R-50-FPN-RETINANET"
  RESNETS:
    BACKBONE_OUT_CHANNELS: 256
    STAGE_WITH_DCN: (False, True, True, True)
    WITH_MODULATED_DCN: False
    DEFORMABLE_GROUPS: 1
    STAGE_WITH_GCB: (False, True, True, True)
  RETINANET:
    USE_C5: False
  FCOS:
    NUM_CLASSES: 31
    FPN_STRIDES: [8, 16, 32, 64, 128]
    INFERENCE_TH: 0.05
    NMS_TH: 0.6
    PRE_NMS_TOP_N: 1000
    NORM_REG_TARGETS: True
    CENTERNESS_ON_REG: True
    CENTER_SAMPLING_RADIUS: 1.5
    IOU_LOSS_TYPE: "giou"
  STFT:
    OFFSET_WEIGHT_STD: 0.01
    IOU_THRESH: 0.1
    BBOX_STD: [0.5, 0.5, 0.5, 0.5]
    REG_BETA: 0.11
DATASETS:
  TRAIN: ("VID_train_15frames",)
  TEST: ("VID_val_videos",)
INPUT:
  MIN_SIZE_TRAIN: (800,)
  MAX_SIZE_TRAIN: 1333
  MIN_SIZE_TEST: 800
  MAX_SIZE_TEST: 1333
DATALOADER:
  SIZE_DIVISIBILITY: 32
SOLVER:
  BASE_LR: 0.0005
  WEIGHT_DECAY: 0.0001
  IMS_PER_BATCH: 3
  WARMUP_METHOD: "linear"
  WARMUP_ITERS: 500
  CHECKPOINT_PERIOD: 125
  TEST_PERIOD: 125
  MAX_ITER: 6000
  LR_TYPE: "step"
  GAMMA: 0.5
  STEPS: (4000, 5000, 5500)
TEST:
  IMS_PER_BATCH: 3
  DETECTIONS_PER_IMG: 300
DATALOADER:
  NUM_WORKERS: 4

Evaluation results are as follows after 125 iterations:

AP50 | motion=   all = 0.0015
Category AP:
airplane        : 0.0099
antelope        : 0.0035
bear            : 0.0018
bicycle         : 0.0000
bird            : 0.0012
bus             : 0.0000
car             : 0.0012
cattle          : 0.0000
dog             : 0.0068
domestic_cat    : 0.0002
elephant        : 0.0019
fox             : 0.0000
giant_panda     : 0.0015
hamster         : 0.0083
horse           : 0.0007
lion            : 0.0000
lizard          : 0.0000
monkey          : 0.0002
motorcycle      : 0.0012
rabbit          : 0.0018
red_panda       : 0.0003
sheep           : 0.0000
snake           : 0.0000
squirrel        : 0.0004
tiger           : 0.0012
train           : 0.0007
turtle          : 0.0002
watercraft      : 0.0006
whale           : 0.0000
zebra           : 0.0024

Can you provide some suggestions?

Detection and Localization

请问您在文章中，这两个指标的P,R,F1分别是怎么计算的？PraNet等是分割模型，是如何计算Detection的P,R,F1的？

如何构建一个可训练的网络模型?

老师您好，我看了您STFT的网络架构，并将其理解为一个“检测模型+融合时序信息的修正模块”的两阶段框架。目前，我也正在开发一个类似的模型，只不过我的修正模块获取时序信息和您的方式不同（基于一个跟踪器）。但是，训练时该模型存在loss曲线抖动和修正模块学习不到知识的情况，请问您在搭建这样一个两阶段框架的时候是如何在两个模块拼接的同时又确保其训练的正确性？您有遇到过类似的问题吗？或者您能给我一些关于这样搭建网络的建议吗？

ASU-Mayo Clinic Colonoscopy Video数据集如何获取？

您好，请问本文所提到的ASU-Mayo Clinic Colonoscopy Video数据集该如何获取呢？在该数据集的网址https://polyp.grand-challenge.org/AsuMayo/ 中并未提及该数据集所有者的邮箱，请问您能帮帮我，提供一下该作者的邮箱或者其他联系方式吗？

lingyunwu14 / stft Goto Github PK

stft's People

Contributors

Stargazers

Watchers

Forkers

stft's Issues

Training and testing on VID dataset

Detection and Localization

如何构建一个可训练的网络模型?

ASU-Mayo Clinic Colonoscopy Video数据集如何获取？

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

Jobs