• Stars
    star
    189
  • Rank 204,649 (Top 5 %)
  • Language
    Python
  • License
    Apache License 2.0
  • Created over 2 years ago
  • Updated over 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

General Vision Benchmark, GV-B, a project from OpenGVLab

Introduction

  • We build GV-B(General Vision Benchmark) on Classification, Detection, Segmentation and Depth Estimation including 26 datasets for model evaluation.

  • It is recommended to evaluate with low-data regime, using only 10% training data.

  • The parameters of model backbone will be frozen during training, as known as 'linear probe'.

  • Face Detection and Depth Estimation is not provided for now, you may evaluate via official repo if needed.

  • Specifically, we use central_model.py in our repo to represent the implementation of Up-G models.

    🏡 Homepage | 📘 Documentation | 👀 Model Zoo

Task Supported

  • Object Classification
  • Object Detection (VOC Detection)
  • Pedestrian Detection (CityPersons Detection)
  • Semantic Segmentation (VOC Segmentation)
  • Face Detection (WiderFace Detection)
  • Depth Estimation (Kitti/NYU-v2 Depth Estimation)

Installation

Requirements

Install Dependencies

a. Create a conda virtual environment and activate it.

conda create -n open-mmlab python=3.8 -y
conda activate open-mmlab

b. Install PyTorch and torchvision following the official instructions, e.g.:

conda install pytorch torchvision -c pytorch
Make sure that your compilation CUDA version and runtime CUDA version match.
You can check the supported CUDA version for precompiled packages on the
[PyTorch website](https://pytorch.org/).

c. Install openmm package via pip (mmcls, mmdet, mmseg):

pip install mmcls
pip install mmdet
pip install mmsegmentation

Usage

This section provide basic tutorials about the usage of GV-B.

Prepare datasets

For each evaluation task, you can follow the official repo tutorial for data preparation.

mmclassification (take flowers for example)
├── data
│   ├── flowers
│   │   ├── train/
│   │   ├── test/
│   │   ├── train_meta.list
│   │   ├── test_meta.list
mmdetection
├── data
│   ├── citypersons
│   │   ├── annotations
│   │   ├── leftImg8bit
│   │   │   ├── train
│   │   │   ├── val
│   ├── VOCdevkit
│   │   ├── VOC2007
│   │   ├── VOC2012
mmsegmentation
├── data
│   ├── VOCdevkit
│   │   ├── VOC2012
│   │   │   ├── JPEGImages
│   │   │   ├── SegmentationClass
│   │   │   ├── ImageSets
│   │   │   │   ├── Segmentation
│   │   ├── VOCaug
│   │   │   ├── dataset
│   │   │   │   ├── cls

Model evaluation

We use MIM to submit evaluation in GV-B.

a.If you run on a cluster managed with slurm, you can use the script mim_slurm_train.sh. (This script also supports single machine training.)

sh tools/mim_slurm_train.sh $PARTITION $TASK $CONFIG $WORK_DIR

## mmcls as an example
sh tools/mim_slurm_train.sh GVT mmcls configs/cls/linear_probe/mnb4_Up-E-C_pretrain_flowers_10p.py /path/to/your/project

b.If you run on w/o slurm. (More details can be found in docs of openmim)

PYTHONPATH='.':$PYTHONPATH mim train $TASK $CONFIG $WORK_DIR
  • PARTITION: The partition you are using
  • WORK_DIR: The directory to save logs and checkpoints
  • CONFIG: Config files corresponding to tasks.

Detailed Tutorials

Currently, we provide tutorials (mmclassification for example) for further development.

Benchmark(with Hyperparameter searching)

CLS DET SEG DEP
10% data Cifar10 Cifar100 Food Pets Flowers Sun Cars Dtd Caltech Aircraft Svhn Eurosat Resisc45 Retinopathy Fer2013 Ucf101 Gtsrb Pcam Imagenet Kinetics700 VOC07+12 WIDER FACE CityPersons VOC2012 KITTI NYUv2
Up-A R50 92.4 73.5 75.8 85.7 94.6 57.9 52.7 65.0 88.5 28.7 61.4 93.8 82.9 73.8 55.0 71.1 75.1 82.9 71.9 35.2 76.3 90.3/88.3/70.7 24.6/59.0 62.54 3.181 0.456
MN-B4 96.1 82.9 84.3 89.8 98.3 66.0 61.4 66.8 92.8 32.5 60.4 92.7 85.8 75.6 56.5 76.9 74.4 84.3 77.2 39.4 74.9 89.3/87.6/71.4 26.5/61.8 65.71 3.565 0.482
MN-B15 98.2 87.8 93.9 92.8 99.6 72.3 59.4 70.0 93.8 64.8 58.6 95.3 91.9 77.9 62.8 85.4 76.2 87.8 86.0 52.9 78.4 93.6/91.8/77.2 17.7/49.5 60.68 2.423 0.383
Up-E C-R50 91.9 71.2 80.7 88.8 94.0 57.4 67.9 62.7 85.5 73.9 57.6 93.7 83.6 75.4 54.1 69.6 73.9 85.7 72.5 34.6 72.2 89.7/87.6/68.1 22.4/58.3 57.66 3.214 0.501
D-R50 86.4 57.3 53.9 31.4 44.0 39.8 8.6 44.6 72.5 15.8 64.2 89.1 72.8 73.6 46.6 57.4 67.5 81.7 45.0 25.2 87.7 93.8/92.0/75.5 15.8/41.5 62.3 3.09 0.45
S-R50 78.3 46.6 45.1 24.2 33.9 38.0 5.0 41.4 50.2 8.5 51.5 89.9 76.4 74.0 44.8 42.0 64.0 80.8 34.9 19.7 75.0 87.4/85.7/66.4 19.6/53.3 71.9 3.12 0.45
C-MN-B4 96.7 83.2 89.2 91.9 98.2 66.7 67.7 66.3 91.9 77.2 57.8 94.4 88.0 77.0 56.6 78.5 77.3 85.6 80.5 44.2 73.7 89.6/88.0/71.1 30.3/65.0 65.8 3.54 0.46
D-MN-B4 91.5 67.0 61.4 44.4 57.2 41.8 12.1 41.2 80.6 25.1 68.0 90.7 74.6 74.3 50.3 61.7 74.2 81.9 57.0 29.3 89.3 94.6/92.6/76.5 14.0/43.8 73.1 3.05 0.40
S-MN-B4 83.5 57.2 68.3 70.8 85.8 52.9 25.9 52.8 81.6 17.7 56.1 91.3 83.6 74.5 49.0 55.2 68.0 84.3 61.0 27.4 78.7 89.5/87.9/71.4 19.4/53.0 79.6 3.06 0.41
C-MN-B-15 98.7 90.1 94.7 95.1 99.7 75.7 74.9 73.6 94.4 91.8 66.7 96.2 92.8 77.6 62.3 87.7 83.3 87.5 87.2 54.7 80.4 93.2/91.4/75.7 29.5/59.9 70.6 2.63 0.37
D-MN-B-15 92.2 67.9 69.0 33.9 59.5 45.4 13.8 46.3 82.0 26.6 65.4 90.1 79.1 76.0 53.2 63.7 74.4 83.3 62.2 33.7 89.4 95.8/94.4/80.1 10.5/42.4 77.2 2.72 0.37
Up-G R50 92.9 73.7 81.1 88.9 94.0 58.6 68.6 63.0 86.1 74.0 57.9 94.4 84.0 75.7 54.3 70.8 74.3 85.9 72.6 34.8 87.7 93.9/92.2/77.0 14.7/46.0 66.19 2.835 0.39
MN-B4 96.7 83.9 89.2 92.1 98.2 66.7 67.7 66.5 91.9 77.2 57.8 94.4 88.0 77.0 57.1 79 77.7 86 80.5 44.2 89.1 94.9/92.8/76.5 12.0/50.5 71.4 2.94 0.40
MN-B15 98.7 90.4 94.5 95.4 99.7 74.4 75.4 74.2 94.5 91.8 66.7 96.3 92.7 77.9 63.1 88 83.6 88 87.1 54.7 89.8 95.9/94.2/79.6 10.5/41.3 77.3 2.71 0.37

More Repositories

1

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Python
5,753
star
2

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Python
5,717
star
3

DragGAN

Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" (DragGAN 全功能实现,在线Demo,本地部署试用,代码、模型已全部开源,支持Windows, macOS, Linux)
Python
4,996
star
4

InternGPT

InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)
Python
3,198
star
5

Ask-Anything

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
Python
2,984
star
6

InternImage

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Python
2,502
star
7

InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
Python
1,392
star
8

VisionLLM

VisionLLM Series
Python
874
star
9

VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding
Python
787
star
10

OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
Python
691
star
11

VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
Python
486
star
12

DCNv4

[CVPR 2024] Deformable Convolution v4
Python
463
star
13

all-seeing

[ICLR 2024 & ECCV 2024] The All-Seeing Projects: Towards Panoptic Visual Recognition&Understanding and General Relation Comprehension of the Open World"
Python
452
star
14

GITM

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
445
star
15

Multi-Modality-Arena

Chatbot Arena meets multi-modality! Multi-Modality Arena allows you to benchmark vision-language models side-by-side while providing images as inputs. Supports MiniGPT-4, LLaMA-Adapter V2, LLaVA, BLIP-2, and many more!
Python
428
star
16

Vision-RWKV

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures
Python
352
star
17

CaFo

[CVPR 2023] Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners
Python
344
star
18

PonderV2

PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
Python
311
star
19

LAMM

[NeurIPS 2023 Datasets and Benchmarks Track] LAMM: Multi-Modal Large Language Models and Applications as AI Agents
Python
296
star
20

UniFormerV2

[ICCV2023] UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
Python
280
star
21

unmasked_teacher

[ICCV2023 Oral] Unmasked Teacher: Towards Training-Efficient Video Foundation Models
Python
276
star
22

OmniCorpus

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
Python
259
star
23

HumanBench

This repo is official implementation of HumanBench (CVPR2023)
Python
231
star
24

Instruct2Act

Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
Python
223
star
25

EfficientQAT

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models
Python
198
star
26

ControlLLM

ControlLLM: Augment Language Models with Tools by Searching on Graphs
Python
181
star
27

InternVideo2

152
star
28

UniHCP

Official PyTorch implementation of UniHCP
Python
149
star
29

efficient-video-recognition

Python
114
star
30

SAM-Med2D

Official implementation of SAM-Med2D
Jupyter Notebook
114
star
31

EgoVideo

[CVPR 2024 Champions] Solutions for EgoVis Chanllenges in CVPR 2024
Jupyter Notebook
103
star
32

DiffRate

[ICCV 23]An approach to enhance the efficiency of Vision Transformer (ViT) by concurrently employing token pruning and token merging techniques, while incorporating a differentiable compression rate.
Jupyter Notebook
86
star
33

MMT-Bench

ICML'2024 | MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI
Python
85
star
34

Awesome-DragGAN

Awesome-DragGAN: A curated list of papers, tutorials, repositories related to DragGAN
75
star
35

MM-NIAH

This is the official implementation of the paper "Needle In A Multimodal Haystack"
Python
70
star
36

M3I-Pretraining

69
star
37

STM-Evaluation

Python
69
star
38

MUTR

[AAAI 2024] Referred by Multi-Modality: A Unified Temporal Transformers for Video Object Segmentation
Python
65
star
39

LCL

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
Python
63
star
40

ChartAst

ChartAssistant is a chart-based vision-language model for universal chart comprehension and reasoning.
Python
60
star
41

LORIS

Long-Term Rhythmic Video Soundtracker, ICML2023
Python
54
star
42

DDPS

Official Implementation of "Denoising Diffusion Semantic Segmentation with Mask Prior Modeling"
Python
53
star
43

Awesome-LLM4Tool

A curated list of the papers, repositories, tutorials, and anythings related to the large language models for tools
52
star
44

PIIP

NeurIPS 2024 Spotlight ⭐️ Parameter-Inverted Image Pyramid Networks (PIIP)
Python
51
star
45

InternVL-MMDetSeg

Train InternViT-6B in MMSegmentation and MMDetection with DeepSpeed
Jupyter Notebook
50
star
46

GUI-Odyssey

GUI Odyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUI Odyssey consists of 7,735 episodes from 6 mobile devices, spanning 6 types of cross-app tasks, 201 apps, and 1.4K app combos.
Python
47
star
47

Siamese-Image-Modeling

[CVPR 2023]Implementation of Siamese Image Modeling for Self-Supervised Vision Representation Learning
Python
33
star
48

De-focus-Attention-Networks

Learning 1D Causal Visual Representation with De-focus Attention Networks
Python
28
star
49

Multitask-Model-Selector

Implementation of Foundation Model is Efficient Multimodal Multitask Model Selector
Python
27
star
50

Official-ConvMAE-Det

Python
13
star
51

perception_test_iccv2023

Champion Solutions repository for Perception Test challenges in ICCV2023 workshop.
Python
13
star
52

opengvlab.github.io

12
star
53

MovieMind

9
star
54

EmbodiedGPT

5
star
55

DriveMLM

3
star
56

.github

2
star