mmfewshot is an open source few shot learning toolbox based on PyTorch

Overview

Introduction

English | 简体中文

Documentation actions codecov PyPI LICENSE Average time to resolve an issue Percentage of issues still open

mmfewshot is an open source few shot learning toolbox based on PyTorch. It is a part of the OpenMMLab project.

The master branch works with PyTorch 1.5+. The compatibility to earlier versions of PyTorch is not fully tested.

Documentation: https://mmfewshot.readthedocs.io/en/latest/.

Major features

  • Support multiple tasks in Few Shot Learning

    MMFewShot provides unified implementation and evaluation of few shot classification and detection.

  • Modular Design

    We decompose the few shot learning framework into different components, which makes it much easy and flexible to build a new model by combining different modules.

  • Strong baseline and State of the art

    The toolbox provides strong baselines and state-of-the-art methods in few shot classification and detection.

License

This project is released under the Apache 2.0 license.

Model Zoo

Supported algorithms:

classification
Detection

Changelog

Installation

Please refer to install.md for installation of mmfewshot.

Getting Started

Please see getting_started.md for the basic usage of mmfewshot.

Citation

If you find this project useful in your research, please consider cite:

@misc{mmfewshot2021,
    title={OpenMMLab Few Shot Learning Toolbox and Benchmark},
    author={mmfewshot Contributors},
    howpublished = {\url{https://github.com/open-mmlab/mmfewshot}},
    year={2021}
}

Contributing

We appreciate all contributions to improve mmfewshot. Please refer to CONTRIBUTING.md in MMFewShot for the contributing guideline.

Acknowledgement

mmfewshot is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new methods.

Projects in OpenMMLab

  • MMCV: OpenMMLab foundational library for computer vision.
  • MIM: MIM Installs OpenMMLab Packages.
  • MMClassification: OpenMMLab image classification toolbox and benchmark.
  • MMDetection: OpenMMLab detection toolbox and benchmark.
  • MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
  • MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
  • MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
  • MMTracking: OpenMMLab video perception toolbox and benchmark.
  • MMPose: OpenMMLab pose estimation toolbox and benchmark.
  • MMEditing: OpenMMLab image and video editing toolbox.
  • MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding.
  • MMGeneration: OpenMMLab image and video generative models toolbox.
  • MMFlow: OpenMMLab optical flow toolbox and benchmark.
  • MMFewShot: OpenMMLab FewShot Learning Toolbox and Benchmark.
Comments
  • about result reimplementation of meta-rcnn

    about result reimplementation of meta-rcnn

    When trying to reproduce results of meta-rcnn and TFA, under 1 shot setting of split1, I find that reproduced results of meta-rcnn is much higher, which is confusing.In paper of meta-rcnn(this 19.9 is the result i want to get): image

    In paper of TFA: image

    Result in paper shows that result of split1 under 1 shot setting is 19.9. But my results is much higher: base training : mAP is 76.2 finetunning : all class is 47.40, novel class is 38.80, base class is 50.53 Which is much higher than results in paper. This is confusing. Besides, in the README.md of meta-rcnn, results are even higher: image

    under split1 1 shot setting, the results of TFA I get is 40.4 which is basically the same as the paper report.

    Could you please kindly answer my questions?

    opened by JulioZhao97 8
  • confused about `samples_per_gpu` of meta_dataloader

    confused about `samples_per_gpu` of meta_dataloader

    https://github.com/open-mmlab/mmfewshot/blob/486c8c2fd7929880eab0dfcd73a3dd3a512ddfbe/configs/detection/base/datasets/nway_kshot/base_voc.py#L106

    Hi, thanks for your great work in fsod. I want to know why the value of samples_per_gpu is not 15 instead of 16 for voc base training. Hope you can help me.

    opened by Wei-i 8
  • coco dataset?

    coco dataset?

    我的coco数据目录是这样的: data --coco ----annotations ----train2014 ----val2014 --few_shot_ann ----coco ------benchmark_10shot -------- ... 当我运行fsce下的coco预训练config时,会报错:no such file or directory: 'data/few_shot_ann/coco/annotaions/train.json' 请问这个train.json是哪里来的,预训练的标签不是应该调用coco文件夹下的annotations吗? 另外我在data preparation找到一个trainvalno5k.json和5k.json,请问是这两个json文件吗? 期待您的回答!

    opened by kike-0304 6
  • RuntimeError: The expanded size of the tensor (21) must match the existing size (54) at non-singleton dimension 0.  Target sizes: [21, 1024].  Tensor sizes: [54, 1024]

    RuntimeError: The expanded size of the tensor (21) must match the existing size (54) at non-singleton dimension 0. Target sizes: [21, 1024]. Tensor sizes: [54, 1024]

    Traceback (most recent call last): File "/home/lbc/miniconda3/envs/mmfewshot/lib/python3.7/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/home/lbc/miniconda3/envs/mmfewshot/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/lbc/mmfewshot-main/tools/detection/misc/initialize_bbox_head.py", line 289, in <module> main() File "/home/lbc/mmfewshot-main/tools/detection/misc/initialize_bbox_head.py", line 278, in main args) File "/home/lbc/mmfewshot-main/tools/detection/misc/initialize_bbox_head.py", line 169, in random_init_checkpoint new_weight[:prev_cls] = pretrained_weight[:prev_cls] RuntimeError: The expanded size of the tensor (21) must match the existing size (54) at non-singleton dimension 0. Target sizes: [21, 1024]. Tensor sizes: [54, 1024]

    The process of fsce on my own coco format datasets is:

    1. Base Training : ckpt(step1)
    2. step two: ues the best val pth of step 1 for train? python3.7 -m tools.detection.misc.initialize_bbox_head --src1 ./work_dirs/fsce_r101_fpn_coco_base-training/best_bbox_mAP_iter_105000.pth --method random_init --save-dir ./work_dirs/fsce_r101_fpn_coco-split1_base-training
    opened by Williamlizl 6
  • Fix tabular printing of dataset information

    Fix tabular printing of dataset information

    Motivation

    When the length of the last row_data is less than 10 and greater than 0, the row_data will not be printed

    Modification

    When the last row_data is not empty, add to table_data

    opened by LiangYang666 4
  • Few-shot instead of one-shot in demo inference

    Few-shot instead of one-shot in demo inference

    Currently, the demo script (classification) takes only one sample in the support set. It uses the process_support_images() method to forward the support set. How to modify this in order to allow for more than one sample in the support set?

    One idea could be to place another set of support images in a different folder and then forward that as well. Then the model.before_forward_support() method can be modified if it resets the features. For e.g. for meta_baseline_head, it is resetting saved features.

    Then (again for meta_baseline), meta_baseline_head.before_forward_query would also have to be modified since it is replacing the self.mean_support_feats with the mean of the new support set.

    Would these two changes in this case be enough to adapt for a few-shot instead of a one-shot inference?

    opened by rlleshi 4
  • How does it work

    How does it work

    According to the document, the following errors occur during training. I don't know how to solve them. Has anyone encountered them. TypeError: init() got an unexpected keyword argument 'persistent_workers'

    opened by isJunCheng 3
  • Question about the training of MatchingNetwork

    Question about the training of MatchingNetwork

    Hi, Great Job.

    I have some questions about the training process of the matching network(classification)

    • In this line, https://github.com/open-mmlab/mmfewshot/blob/31583cccb8ef870c9e688b1dc259263b73e58884/configs/classification/matching_net/mini_imagenet/matching-net_conv4_1xb105_mini-imagenet_5way-1shot.py?_pjax=%23js-repo-pjax-container%2C%20div%5Bitemtype%3D%22http%3A%2F%2Fschema.org%2FSoftwareSourceCode%22%5D%20main%2C%20%5Bdata-pjax-container%5D#L28 You use num_shots=5 for training 5-way-1-shot, is this a bug?
    • The batch size shown in the result table is 64, I would like to know whether this number is the training batch size or test batch size?
    • How many gaps between the meta-val and meta-test split in your experiment?
      • In the log of matching_net 5-way-1-shot, the max accuracy is about 51%, while the test result is 53%, does it means there exists ~2 points between two sets?

    Thanks, Best

    opened by tonysy 3
  • meta_test_head is None on demo

    meta_test_head is None on demo

    The error occurs when running demo_metric_classifier_1shot_inference with a custom trained NegMargin model. The meta_test_head is None. Testing the model with dist_test works as expected though. I am not sure why it didn't save the meta test head. A comment here says that it is only built and run on testing. I am not sure what that means though.

    The model config is the same as the standard in other config files:

    model = dict(
        type='NegMargin',
        backbone=dict(type='Conv4'),
        head=dict(
            type='NegMarginHead',
            num_classes=6,
            in_channels=1600,
            metric_type='cosine',
            margin=-0.01,
            temperature=10.0),
        meta_test_head=dict(
            type='NegMarginHead',
            num_classes=6,
            in_channels=1600,
            metric_type='cosine',
            margin=0.0,
            temperature=5.0))
    

    Otherwise, the config file itself is similar to other neg_margin config files for the cube dataset.

    opened by rlleshi 3
  • Don't find the “frozen_parameters” parameter in the relevant source code

    Don't find the “frozen_parameters” parameter in the relevant source code

    I found that the “frozen_parameters” parameter is used in many detection models, but I have not found where this parameter is used in the relevant source code. Which part of the source code should I see?

    opened by wwwbq 2
  • FewShotCocoDefaultDataset中coco_benchmark的ann_file路径无法自定义

    FewShotCocoDefaultDataset中coco_benchmark的ann_file路径无法自定义

    在mmfewshot/detection/datasets/coco.py/FewShotCocoDefaultDataset 中的coco_benchmark固定了数据集路径为f'data/few_shot_ann/coco/benchmark_{shot}shot/full_box_{shot}shot_{class_name}_trainval.json'。但是我的few_shot_ann路径和上面不同,并且FewShotCocoDefaultDataset没有办法接受数据集路径的参数,希望可以增加此参数

    opened by wwwbq 2
  • 运行mpsr第一阶段报错~

    运行mpsr第一阶段报错~

    Traceback (most recent call last): File "/root/mmfewshot/./tools/detection/train.py", line 236, in main() File "/root/mmfewshot/./tools/detection/train.py", line 225, in main train_detector( File "/root/mmfewshot/mmfewshot/detection/apis/train.py", line 48, in train_detector data_loaders = [build_dataloader(ds, **train_loader_cfg) for ds in dataset] File "/root/mmfewshot/mmfewshot/detection/apis/train.py", line 48, in data_loaders = [build_dataloader(ds, **train_loader_cfg) for ds in dataset] File "/root/mmfewshot/mmfewshot/detection/datasets/builder.py", line 311, in build_dataloader data_loader = TwoBranchDataloader( TypeError: init() got an unexpected keyword argument 'persistent_workers' Killing subprocess 9272 Traceback (most recent call last): File "/opt/conda/envs/pytorch1.8/lib/python3.9/runpy.py", line 197, in _run_module_as_main return _run_code(code, main_globals, None, File "/opt/conda/envs/pytorch1.8/lib/python3.9/runpy.py", line 87, in _run_code exec(code, run_globals) File "/opt/conda/envs/pytorch1.8/lib/python3.9/site-packages/torch/distributed/launch.py", line 340, in main() File "/opt/conda/envs/pytorch1.8/lib/python3.9/site-packages/torch/distributed/launch.py", line 326, in main sigkill_handler(signal.SIGTERM, None) # not coming back File "/opt/conda/envs/pytorch1.8/lib/python3.9/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd) subprocess.CalledProcessError: Command '['/opt/conda/envs/pytorch1.8/bin/python', '-u', './tools/detection/train.py', '--local_rank=0', 'configs/detection/mpsr/voc/split1/mpsr_r101_fpn_2xb2_voc-split1_base-training.py', '--launcher', 'pytorch']' returned non-zero exit status 1.

    opened by DaDogs 1
  • Where should I put my few shot dataset?

    Where should I put my few shot dataset?

    Since few shot dataset is just for finetuning the model and the test.py won't save the change of the model, where should I put my fewshot dataset? training set or validation set? In that way, I could use the pth file to predict my images in the demo.py?

    opened by winnie9802 0
  • The initialization is blocked on building the models in FSClassification

    The initialization is blocked on building the models in FSClassification

    We meet problem when training on classification models. We test several times, the code is blocked on this line of command in classification.api.train 截屏2022-10-15 下午12 31 58

    opened by jwfanDL 0
  • Request to add the ability to read tiff datasets

    Request to add the ability to read tiff datasets

    When I was studying the process of small sample learning, I came across tiff images in the data set. At this point, there is a problem with the dataset loading, would like to ask if you can add a tiff format read method.

    opened by Djn-swjtu 0
Releases(v0.1.0)
  • v0.1.0(Nov 24, 2021)

    Main Features

    • Support few shot classification and few shot detection.
    • For few shot classification, support fine-tune based methods (Baseline, Baseline++, NegMargin); metric-based methods (MatchingNet, ProtoNet, RelationNet, MetaBaseline); meta-learning based method (MAML).
    • For few shot detection, support fine-tune based methods (TFA, FSCE, MPSR); Meta-learning based methods (MetaRCNN, FsDetView, AttentionRPN).
    • Provide checkpoints and log files for all of the methods above.
    Source code(tar.gz)
    Source code(zip)
The versatile ocean simulator, in pure Python, powered by JAX.

Veros is the versatile ocean simulator -- it aims to be a powerful tool that makes high-performance ocean modeling approachable and fun. Because Veros

TeamOcean 245 Dec 20, 2022
Pytorch implementation of few-shot semantic image synthesis

Few-shot Semantic Image Synthesis Using StyleGAN Prior Our method can synthesize photorealistic images from dense or sparse semantic annotations using

40 Sep 26, 2022
Neural style transfer in PyTorch.

style-transfer-pytorch An implementation of neural style transfer (A Neural Algorithm of Artistic Style) in PyTorch, supporting CPUs and Nvidia GPUs.

Katherine Crowson 395 Jan 06, 2023
Model Zoo for MindSpore

Welcome to the Model Zoo for MindSpore In order to facilitate developers to enjoy the benefits of MindSpore framework, we will continue to add typical

MindSpore 226 Jan 07, 2023
Official implementation of Densely connected normalizing flows

Densely connected normalizing flows This repository is the official implementation of NeurIPS 2021 paper Densely connected normalizing flows. Poster a

Matej Grcić 31 Dec 12, 2022
PyTorch/GPU re-implementation of the paper Masked Autoencoders Are Scalable Vision Learners

Masked Autoencoders: A PyTorch Implementation This is a PyTorch/GPU re-implementation of the paper Masked Autoencoders Are Scalable Vision Learners: @

Meta Research 4.8k Jan 04, 2023
Machine Learning automation and tracking

The Open-Source MLOps Orchestration Framework MLRun is an open-source MLOps framework that offers an integrative approach to managing your machine-lea

873 Jan 04, 2023
MMRazor: a model compression toolkit for model slimming and AutoML

Documentation: https://mmrazor.readthedocs.io/ English | 简体中文 Introduction MMRazor is a model compression toolkit for model slimming and AutoML, which

OpenMMLab 899 Jan 02, 2023
Red Team tool for exfiltrating files from a target's Google Drive that you have access to, via Google's API.

GD-Thief Red Team tool for exfiltrating files from a target's Google Drive that you(the attacker) has access to, via the Google Drive API. This includ

Antonio Piazza 39 Dec 27, 2022
Finite-temperature variational Monte Carlo calculation of uniform electron gas using neural canonical transformation.

CoulombGas This code implements the neural canonical transformation approach to the thermodynamic properties of uniform electron gas. Building on JAX,

FermiFlow 9 Mar 03, 2022
pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"

Unofficial implementation: MoCo: Momentum Contrast for Unsupervised Visual Representation Learning (Paper) InsDis: Unsupervised Feature Learning via N

Zhiqiang Shen 16 Nov 04, 2020
This is the repository for Learning to Generate Piano Music With Sustain Pedals

SusPedal-Gen This is the official repository of Learning to Generate Piano Music With Sustain Pedals Demo Page Dataset The dataset used in this projec

Joann Ching 12 Sep 02, 2022
Official code release for "Learned Spatial Representations for Few-shot Talking-Head Synthesis" ICCV 2021

Official code release for "Learned Spatial Representations for Few-shot Talking-Head Synthesis" ICCV 2021

Moustafa Meshry 16 Oct 05, 2022
In Search of Probeable Generalization Measures

In Search of Probeable Generalization Measures Exciting News! In Search of Probeable Generalization Measures has been accepted to the International Co

Mahdi S. Hosseini 6 Sep 11, 2022
We will release the code of "ConTNet: Why not use convolution and transformer at the same time?" in this repo

ConTNet Introduction ConTNet (Convlution-Tranformer Network) is proposed mainly in response to the following two issues: (1) ConvNets lack a large rec

93 Nov 08, 2022
Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pytorch Lightning 1.4k Jan 01, 2023
Flow is a computational framework for deep RL and control experiments for traffic microsimulation.

Flow Flow is a computational framework for deep RL and control experiments for traffic microsimulation. See our website for more information on the ap

867 Jan 02, 2023
Transfer Learning Remote Sensing

Transfer_Learning_Remote_Sensing Simulation R codes for data generation and visualizations are in the folder simulation. Experiment: California Housin

2 Jun 21, 2022
Jax/Flax implementation of Variational-DiffWave.

jax-variational-diffwave Jax/Flax implementation of Variational-DiffWave. (Zhifeng Kong et al., 2020, Diederik P. Kingma et al., 2021.) DiffWave with

YoungJoong Kim 37 Dec 16, 2022