Monk_Object_Detection

A one-stop repository for low-code easily-installable object detection pipelines.

Documentation

• LINK

Important Elements

• A) Training Engine

  • Train models on custom dataset witjh low code syntax
  • Pretrained examples on variety of datasets
  • Useful to train your own detector

• B) Inference Engine

  • Original pretrained models (from original authors and implementations) for inferencing and analysing
  • Pretrained models on coco, voc, cityscpaes, type datasets
  • Useful to analyse which algoeithm works best for you
  • Useful to generate semi-accurate annotations (coco, pascal-voc, yolo formats) on a new dataset

Training engine - Pipelines presented as jupyter notebooks - see example_notebooks

(See the licenses for each pipeline and use accordingly)

• A) GluonCV Finetune

  • Original Implementation
  • Functional Documentation
    • SSD with Vgg16
    • SSD with Resnet50
    • SSD with Resnet101
    • SSD with MobileNet1.0
    • YoloV3 with Darknet53
    • YoloV3 with MobileNet1.0

• B) TorchVision Finetune: Original

  • Original Implementation
  • Functional Documentation
    • Faster-RCNN with MobileNet2.0

• C) MX-RCNN: Original

  • Original Implementation
  • Functional Documentation
    • Faster-RCNN with VGG16
    • Faster-RCNN with Resnet50
    • Faster-RCNN with Resnet101

• D) Efficient-Det: Original

  • Original Implementation
  • Functional Documentation

• E) Pytorch-Retinanet: Original

  • Original Implementation
  • Functional Documentation
    • Resnet18
    • Resnet34
    • Resnet50
    • Resnet101
    • Resnet152

• F) CornerNet-Lite: Original

  • Original Implementation
  • Functional Documentation
    • CornerNet-Saccade
    • CornerNet-Squeeze

• G) YOLOV3: Original

  • Original Implementation
  • Functional Documentation
    • yolov3
    • yolov3s
    • yolov3-spp
    • yolov3-spp3
    • yolov3-tiny
    • yolov3-spp-matrix
    • csresnext50-panet-spp

• H) RFBNet:

  • Original Implementation
  • Functional Documentation
    • VGG16
    • E_VGG16
    • MobileNet

• I) Segmentation_Models:

  • Original Implementation
  • [Functional Documentation]
    • Unet
    • FPN
    • Linknet
    • PSPNet

• J) Pytorch_Efficientdet:

  • Original Implementation
  • [Functional Documentation]
    • efficientdet-d0.pth
    • efficientdet-d1.pth
    • efficientdet-d2.pth
    • efficientdet-d3.pth
    • efficientdet-d4.pth
    • efficientdet-d5.pth
    • efficientdet-d6.pth
    • efficientdet-d7.pth

Inference Engine

(See the licenses for each pipeline and use accordingly)

• A) GluonCV Finetune

  • Original Implementation
  • Pretrained models on
    • COCO Dataset
    • Pascal VOC Dataset
  • Models using
    • SSD
    • faster-rcnn
    • Yolo-V3
    • CenterNet

• B) EfficientDet Pytorch

  • Original Implementation
  • Pretrained models on
    • COCO Dataset
  • Models using efficient network variants

• C) DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution.

  • Original Implementation
  • Pretrained models on
    • COCO Dataset
  • Models using
    • Resnet-50
    • RexNext-101

Installation - Inference engine

• Check - Monk_Object_Detection/inference_engine/

Installation - Training engine

• A) GluonCV Finetune

  • Check - Monk_Object_Detection/1_gluoncv_finetune/

• B) TorchVision Finetune

  • Check - Monk_Object_Detection/2_pytorch_finetune/

• C) MX-RCNN

  • Check - Monk_Object_Detection/3_mxrcnn/

• D) Efficient-Det

  • Check - Monk_Object_Detection/4_efficientdet/

• E) Pytorch-Retinanet

  • Check - Monk_Object_Detection/5_pytorch_retinanet/

• F) CornerNet-Lite

  • Check - Monk_Object_Detection/6_cornernet_lite/

• G) YoloV3

  • Check - Monk_Object_Detection/7_yolov3/

• H) RFBNet

  • Check - Monk_Object_Detection/8_pytorch_rfbnet

• I) Segmentation_Models

  • Check - Monk_Object_Detection/9_segmentation_models

Author

Tessellate Imaging - https://www.tessellateimaging.com/

Check out Monk AI - (https://github.com/Tessellate-Imaging/monk_v1)

Monk features
    - low-code
    - unified wrapper over major deep learning framework - keras, pytorch, gluoncv
    - syntax invariant wrapper

Enables developers
    - to create, manage and version control deep learning experiments
    - to compare experiments across training metrics
    - to quickly find best hyper-parameters

To contribute to Monk AI or Monk Object Detection repository raise an issue in the git-repo or dm us on linkedin

• Abhishek - https://www.linkedin.com/in/abhishek-kumar-annamraju/
• Akash - https://www.linkedin.com/in/akashdeepsingh01/

Copyright

Copyright 2019 onwards, Tessellate Imaging Private Limited Licensed under the Apache License, Version 2.0 (the "License"); you may not use this project's files except in compliance with the License. A copy of the License is provided in the LICENSE file in this repository.