百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
Y

youtube8mchallenge

> 编程语言
开源

Kaggle 2018 年 YouTube-8M 视频理解挑战的第一名解决方案

199 stars0 点赞0 次浏览
访问官网GitHub

工具介绍

Kaggle 2018 年 YouTube-8M 视频理解挑战的第一名解决方案

Next top GB model solution to The 2nd YouTube-8M Video Understanding Challenge

This repository contains all code used by first placed team "Next top GB model" (David and Miha skalic) in the Kaggle's competition The 2nd YouTube-8M Video Understanding Challenge.

The repository is a fork of google's repository and borrows from Wang et al, Miech et al and Skalic et al. Code is released under Apache License Version 2.0.

This readme walks through a specific example to reproduce training, eval, distillation, quantization, graph combination for a single model type.

Citation

@inproceedings{skalic2018building,
  title={Building A Size Constrained Predictive Models for Video Classification},
  author={Skalic, Miha and Austin, David},
  booktitle={European Conference on Computer Vision},
  pages={297--305},
  year={2018},
  organization={Springer}
}

Background

All models herein were trained in single GPU mode and the instructions that follow will reproduce this step. The overall flow for training each model is as follows:

  1. Train model
  2. Evaluate model
  3. (Optional) Perform EMA- Exponentially weighted Moving Average of weights
  4. Quantize model
  5. Perform inference on quantized model
  6. (Optional) If running distillation, create distillation dataset, then repeat from step 1.
  7. Combine multiple graphs into single graph

This readme will walk through all commands to train both stand-alone and a distillation model. For model details for other models see all_models.txt.

Requirements

All code was run using Python 2.7 and Tensorflow 1.8.0. All models were trained on GPU's. The requirements.txt file contains a list of all libraries installed in the environment used for training and testing. While all libraries are not required, the having the full list should ensure complete compatibility with all code.

Training Models

Make sure to set your local paths correctly for the train and save paths:

…

Eval model

Once training is complete, eval is performed as follows:

…

Perform EMA

…

Quantize Model and copy model_flags.json

Change savefile to specific save path

bash

python quantize.py \
  --transform_type quant_uniform \
  --model "$SAVEPATH//NetVLAD_ema/inference_model" \
  --savefile ../trained_models/quants/your_model/inference_model

cp $SAVEPATH//NetVLAD_ema/model_flags.json ../trained_models/quants/your_model

Combine multiple graphs into single graph

graph_ensemble.py takes in 2 or more trained models and combines them into a single graph. Sample usage:

bash
python graph_ensemble.py \
--models ../trained_models/quants/74/inference_model \
        ../trained_models/model_1/inference_model \
        ../trained_models/model_2/inference_model \
        ../trained_models/model_3/inference_model \
--weights 0.3333 0.3333 0.3334  \
--save_folder ../train_models/your_combined_output_graph

Perform Inference

bash

RECORDPATTEST="../data/frame/test"

python inference_gpu.py \
  --train_dir "../trained_models/quants/your_model"  \
  --output_file="./output.csv" \
  --input_data_pattern="$RECORDPATtest/*.tfrecord" \
  --batch_size 200 \
  --sample_all

Create Distillation Set and Train on it.

WARNING: Large dataset creation! Creating a new Distillation set will consume ~1.4TB of data so you'll need to have the storage space available.

bash
python prepare_distill_dataset.py   --batch_size 128   --file_size 512   --input_data_pattern "$RECORDPATVAL/*.tfrecord"   --output_dir "output_folder/train_distill/"   --model_file "../train_models/your_ensemble_model/inference_model"

Training on a distillation dataset can be done using train_distill.py script. Use same flags as in train.py.

Model configurations

File model_configs.xlsx contains the arhitectures of models used in the work.

Trained Model

Trained model as .tar.gz can be downloaded from here. See inference.py for sample usage of the model. Folder feature_extractor contains information on preprocessing custom videos.

Issues· 22 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Python

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月18日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言