mmdetection | OpenMMLab Detection Toolbox and Benchmark | Computer Vision library

 by   open-mmlab Python Version: v3.0.0 License: Apache-2.0

kandi X-RAY | mmdetection Summary

kandi X-RAY | mmdetection Summary

mmdetection is a Python library typically used in Artificial Intelligence, Computer Vision, Deep Learning, Pytorch applications. mmdetection has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can install using 'pip install mmdetection' or download it from GitHub, PyPI.

Results and models are available in the model zoo. Some other methods are also supported in projects using MMDetection.
Support
    Quality
      Security
        License
          Reuse

            kandi-support Support

              mmdetection has a medium active ecosystem.
              It has 24583 star(s) with 8707 fork(s). There are 372 watchers for this library.
              OutlinedDot
              It had no major release in the last 12 months.
              There are 721 open issues and 6412 have been closed. On average issues are closed in 21 days. There are 123 open pull requests and 0 closed requests.
              It has a neutral sentiment in the developer community.
              The latest version of mmdetection is v3.0.0

            kandi-Quality Quality

              mmdetection has 0 bugs and 0 code smells.

            kandi-Security Security

              mmdetection has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.
              mmdetection code analysis shows 0 unresolved vulnerabilities.
              There are 0 security hotspots that need review.

            kandi-License License

              mmdetection is licensed under the Apache-2.0 License. This license is Permissive.
              Permissive licenses have the least restrictions, and you can use them in most projects.

            kandi-Reuse Reuse

              mmdetection releases are available to install and integrate.
              Deployable package is available in PyPI.
              Build file is available. You can build the component from source.
              Installation instructions, examples and code snippets are available.
              mmdetection saves you 24610 person hours of effort in developing the same functionality from scratch.
              It has 76163 lines of code, 2442 functions and 1057 files.
              It has high code complexity. Code complexity directly impacts maintainability of the code.

            Top functions reviewed by kandi - BETA

            kandi has reviewed mmdetection and discovered the below as its top functions. This is intended to give you an instant insight into mmdetection implemented functionality, and help decide if they suit your requirements.
            • Convert model to onnx
            • Preprocess image input
            • Return a list of the keys of the record
            • Return a list of digit version number
            • Visualize a bounding box image
            • Calculate adaptive scales
            • Draws bounding boxes
            • Draws labels
            • Visualize result
            • Visualize a given image
            • Train the model
            • Build a daloader
            • Parse a requirements txt file
            • Perform SW - MSA algorithm on the given query
            • Infer the inference detector
            • Analyze a COCO annotation file
            • Calculate a loss coefficient for a loss function
            • Convert a pre - trained quadratic model to a pk
            • Export scores to ONNX
            • Build a dataloader
            • Generate a random triangle
            • Create a pandas dataframe from images
            • Parse command line arguments
            • Convert MMDetection
            • Convert onnx to Tensorrt
            • Plot the confusion matrix
            • Convert cvt to coco json
            • Generate a random class
            Get all kandi verified functions for this library.

            mmdetection Key Features

            No Key Features are available at this moment for mmdetection.

            mmdetection Examples and Code Snippets

            Tutorial 1: Learn about Configs-An Example of Mask R-CNN
            Pythondot img1Lines of Code : 326dot img1License : Permissive (Apache-2.0)
            copy iconCopy
            model = dict(
                type='MaskRCNN',  # The name of detector
                backbone=dict(  # The config of backbone
                    type='ResNet',  # The type of the backbone, refer to https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/backbones/resnet.p  
            教程 1: 学习配置文件-Mask R-CNN 配置文件示例
            Pythondot img2Lines of Code : 325dot img2License : Permissive (Apache-2.0)
            copy iconCopy
            model = dict(
                type='MaskRCNN',  # 检测器(detector)名称
                backbone=dict(  # 主干网络的配置文件
                    type='ResNet',  # 主干网络的类别,可用选项请参考 https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/backbones/resnet.py#L308
                    depth=50,  # 主干网络的深度,对  
            2: 在自定义数据集上进行训练-准备自定义数据集-COCO标注格式
            Pythondot img3Lines of Code : 162dot img3License : Permissive (Apache-2.0)
            copy iconCopy
            {
                "images": [image],
                "annotations": [annotation],
                "categories": [category]
            }
            
            
            image = {
                "id": int,
                "width": int,
                "height": int,
                "file_name": str,
            }
            
            annotation = {
                "id": int,
                "image_id": int,
                "category_id": in  
            mmdetection - create result gif
            Pythondot img4Lines of Code : 111dot img4License : Non-SPDX (Apache License 2.0)
            copy iconCopy
            # Copyright (c) OpenMMLab. All rights reserved.
            import argparse
            import os
            import os.path as osp
            
            import matplotlib.patches as mpatches
            import matplotlib.pyplot as plt
            import mmcv
            import numpy as np
            
            try:
                import imageio
            except ImportError:
                ima  
            mmdetection - video gpuaccel demo
            Pythondot img5Lines of Code : 94dot img5License : Non-SPDX (Apache License 2.0)
            copy iconCopy
            # Copyright (c) OpenMMLab. All rights reserved.
            import argparse
            
            import cv2
            import mmcv
            import numpy as np
            import torch
            from torchvision.transforms import functional as F
            
            from mmdet.apis import init_detector
            from mmdet.datasets.pipelines import Comp  
            mmdetection - conf-zh cn
            Pythondot img6Lines of Code : 55dot img6License : Non-SPDX (Apache License 2.0)
            copy iconCopy
            # Configuration file for the Sphinx documentation builder.
            #
            # This file only contains a selection of the most common options. For a full
            # list see the documentation:
            # https://www.sphinx-doc.org/en/master/usage/configuration.html
            
            # -- Path setup -  

            Community Discussions

            QUESTION

            faster_rcnn_r50 pretrained converted to ONNX hosted in Triton model server
            Asked 2021-Dec-03 at 21:00

            I went through the mmdetection documentation to convert a pytorch model to onnx here link

            All installations are correct and i'm using onnxruntime==1.8.1, custom operators for ONNX Runtime MMCV_WITH_OPS.

            I'm using the configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py for faster rcnn link and using R-5-FPN pretrained model link

            I used this to convert the pretrained model to onnx and successfully saved an onnx file named fasterrcnn.onnx

            ...

            ANSWER

            Answered 2021-Dec-03 at 21:00

            Looking at the conversion script seems like dets is a combo of boxes plus score

            Source https://stackoverflow.com/questions/70192619

            QUESTION

            Wrong "-1 background" annotations loaded from Custom COCO Dataset using Mmdetection
            Asked 2021-Sep-23 at 15:47
            Introduction

            I'm working using Mmdetection to train a Deformable DETR model using a custom COCO Dataset. Meaning a Custom Dataset using the COCO format of annotations. The dataset uses the same images as the COCO with different "toy" annotations for a "playground" experiment and the annotation file was created using the packages pycocotools and json exclusively.

            I have made five variations of this playground dataset: 2 datasets with three classes (classes 1, 2, and 3), 1 dataset with six classes (classes 1 to 6) and 2 datasets with 7 classes (classes 1 to 7).

            The Problem

            Now, after creating the dataset in mmdetection using mmdet.datasets.build_dataset, I used the following code to check if everything was OK:

            ...

            ANSWER

            Answered 2021-Sep-23 at 15:47

            There was a mismatch between the classes names in the annotation file and the classes names in the mmdetection config object. Correcting those solved the problem.

            Source https://stackoverflow.com/questions/69293877

            QUESTION

            Passing arguments to shell command
            Asked 2021-Jul-25 at 15:27

            I have a shell script that I am executing inside a python script and i want to pass two variables to the script as arguments.I used $ sign but it's not working. this is the shell script:

            ...

            ANSWER

            Answered 2021-Jul-25 at 15:27

            I guess string interpolation can be used to pass your Python variables to the args of the call command. For example, if you use fstring, the code will look like this:

            Source https://stackoverflow.com/questions/68519873

            QUESTION

            How to append all items in the list?
            Asked 2021-Jun-06 at 04:10

            I need to write image_ids in a file which exist in mmdetection class . i tried to get the image_id by img_meta['ori_filename'] and implement this code to write all of the ids

            ...

            ANSWER

            Answered 2021-Jun-06 at 04:10

            I assume you have a variable image_metas where all the images are stored.

            Source https://stackoverflow.com/questions/67855631

            QUESTION

            fatal error: cuda_runtime_api.h: No such file or directory when trying to use cuda in docker
            Asked 2020-Oct-22 at 14:06

            I am trying to build a docker image for a python script that I would like to deploy. This is the first time I am using docker so I'm probably doing something wrong but I have no clue what.

            My System:

            ...

            ANSWER

            Answered 2020-Oct-22 at 13:20

            EDIT: this answer just tells you how to verify what's happening in your docker image. Unfortunately I'm unable to figure out why it is happening.

            How to check it?

            At each step of the docker build, you can see the various layers being generated. You can use that ID to create a temporary image to check what's happening. e.g.

            Source https://stackoverflow.com/questions/64481487

            Community Discussions, Code Snippets contain sources that include Stack Exchange Network

            Vulnerabilities

            No vulnerabilities reported

            Install mmdetection

            Please refer to get_started.md for installation.
            Please see get_started.md for the basic usage of MMDetection. We provide colab tutorial, and full guidance for quick run with existing dataset and with new dataset for beginners. There are also tutorials for finetuning models, adding new dataset, designing data pipeline, customizing models, customizing runtime settings and useful tools. Please refer to FAQ for frequently asked questions.

            Support

            We appreciate all contributions to improve MMDetection. Ongoing projects can be found in out GitHub Projects. Welcome community users to participate in these projects. Please refer to CONTRIBUTING.md for the contributing guideline.
            Find more information at:

            Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items

            Find more libraries

            Stay Updated

            Subscribe to our newsletter for trending solutions and developer bootcamps

            Agree to Sign up and Terms & Conditions

            Share this Page

            share link