DetectionTeamUCAS / Nas_fpn_tensorflow
Licence: mit
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
Stars: ✭ 198
Projects that are alternatives of or similar to Nas fpn tensorflow
Fcos tensorflow
FCOS: Fully Convolutional One-Stage Object Detection.
Stars: ✭ 87 (-56.06%)
Mutual labels: object-detection, jupyter-notebook, coco
Ssd keras
简明 SSD 目标检测模型 keras version（交通标志识别 训练部分见 dev 分支）
Stars: ✭ 152 (-23.23%)
Mutual labels: object-detection, jupyter-notebook
Faster Rcnn tensorflow
This is a tensorflow re-implementation of Faster R-CNN: Towards Real-Time ObjectDetection with Region Proposal Networks.
Stars: ✭ 142 (-28.28%)
Mutual labels: jupyter-notebook, coco
Repo 2018
Deep Learning Summer School + Tensorflow + OpenCV cascade training + YOLO + COCO + CycleGAN + AWS EC2 Setup + AWS IoT Project + AWS SageMaker + AWS API Gateway + Raspberry Pi3 Ubuntu Core
Stars: ✭ 163 (-17.68%)
Mutual labels: jupyter-notebook, coco
Copy Paste Aug
Copy-paste augmentation for segmentation and detection tasks
Stars: ✭ 132 (-33.33%)
Mutual labels: object-detection, jupyter-notebook
Voc2coco
How to create custom COCO data set for object detection
Stars: ✭ 140 (-29.29%)
Mutual labels: object-detection, jupyter-notebook
Yolov4 Cloud Tutorial
This repository walks you through how to Build and Run YOLOv4 Object Detections with Darknet in the Cloud with Google Colab.
Stars: ✭ 153 (-22.73%)
Mutual labels: object-detection, jupyter-notebook
Robust Physical Attack
Physical adversarial attack for fooling the Faster R-CNN object detector
Stars: ✭ 115 (-41.92%)
Mutual labels: object-detection, jupyter-notebook
Shape Detection
🟣 Object detection of abstract shapes with neural networks
Stars: ✭ 170 (-14.14%)
Mutual labels: object-detection, jupyter-notebook
Torchdistill
PyTorch-based modular, configuration-driven framework for knowledge distillation. 🏆18 methods including SOTA are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy.
Stars: ✭ 177 (-10.61%)
Mutual labels: object-detection, coco
Yolov3 Tf2
YoloV3 Implemented in Tensorflow 2.0
Stars: ✭ 2,327 (+1075.25%)
Mutual labels: object-detection, jupyter-notebook
Object detection demo
How to train an object detection model easy for free
Stars: ✭ 130 (-34.34%)
Mutual labels: object-detection, jupyter-notebook
Robust Detection Benchmark
Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)
Stars: ✭ 128 (-35.35%)
Mutual labels: object-detection, jupyter-notebook
Lacmus
Lacmus is a cross-platform application that helps to find people who are lost in the forest using computer vision and neural networks.
Stars: ✭ 142 (-28.28%)
Mutual labels: object-detection, jupyter-notebook
Objectdetection
Some experiments with object detection in PyTorch
Stars: ✭ 117 (-40.91%)
Mutual labels: object-detection, jupyter-notebook
Ios Coreml Yolo
Almost Real-time Object Detection using Apple's CoreML and YOLO v1 -
Stars: ✭ 153 (-22.73%)
Mutual labels: object-detection, jupyter-notebook
Py R Fcn Multigpu
Code for training py-faster-rcnn and py-R-FCN on multiple GPUs in caffe
Stars: ✭ 192 (-3.03%)
Mutual labels: object-detection, jupyter-notebook
Kerasobjectdetector
Keras Object Detection API with YOLK project 🍳
Stars: ✭ 113 (-42.93%)
Mutual labels: object-detection, jupyter-notebook
Colab Mask Rcnn
How to run Object Detection and Segmentation on a Video Fast for Free
Stars: ✭ 114 (-42.42%)
Mutual labels: object-detection, jupyter-notebook
Face mask detection
Face mask detection system using Deep learning.
Stars: ✭ 168 (-15.15%)
Mutual labels: object-detection, jupyter-notebook
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Abstract
This repo is based on FPN, and completed by YangXue.
Train on COCO train2017 and test on COCO val2017 (coco minival).
COCO
| Model | Backbone | Train Schedule | GPU | Image/GPU | FP16 | Box AP |
|---|---|---|---|---|---|---|
| Faster (Face++ & Detectron) | R50v1-FPN | 1X | 8X TITAN Xp | 2 | no | 36.4 |
| Faster (SimpleDet) | R50v1-FPN | 1X | 8X 1080Ti | 2 | no | 36.5 |
| Faster (ours) | R50v1-FPN | 1X | 1X TITAN Xp | 1 | no | 36.1 |
| Faster (ours) | R50v1-FPN | 1X | 4X TITAN Xp | 1 | no | 36.1 |
| Model | Backbone | Pyramid method | Train Schedule | GPU | Image/GPU | Stacks | Dimension | 3x3 relu | Box AP |
|---|---|---|---|---|---|---|---|---|---|
| Faster (ours) | R50v1 | FPN | 1X | 4X TITAN Xp | 1 | 0 | 256 | no | 36.1 |
| Faster (ours) | R50v1 | FPN | 1X | 8X 2080Ti | 1 | 3 | 256 | yes | 35.8 |
| Faster (ours) | R50v1 | NAS-FPN | 1X | 8X 2080Ti | 1 | 3 | 256 | yes | 37.9 |
| Faster (ours) | R50v1 | NAS-FPN | 1X | 8X 2080Ti | 1 | 7 | 256 | yes | 38.1 |
| Faster (ours) | R50v1 | NAS-FPN | 1X | 8X 2080Ti | 1 | 7 | 384 | yes | 38.9 |
My Development Environment
1、python3.5 (anaconda recommend)
2、cuda9.0 (If you want to use cuda8, please set CUDA9 = False in the cfgs.py file.)
3、opencv(cv2)
4、tfplot (optional)
5、tensorflow == 1.12
Download Model
Pretrain weights
1、Please download resnet50_v1, resnet101_v1 pre-trained models on Imagenet, put it to data/pretrained_weights.
2、(Recommend) Or you can choose to use a better backbone, refer to gluon2TF.
- Baidu Drive, password: 5ht9.
- Google Drive
Trained weights
Select a configuration file in the folder ($PATH_ROOT/libs/configs/) and copy its contents into cfgs.py, then download the corresponding weights.
Others
1、COCO dataset related
Compile
cd $PATH_ROOT/libs/box_utils/cython_utils
python setup.py build_ext --inplace
Train
1、If you want to train your own data, please note:
(1) Modify parameters (such as CLASS_NUM, DATASET_NAME, VERSION, etc.) in $PATH_ROOT/libs/configs/cfgs.py
(2) Add category information in $PATH_ROOT/libs/label_name_dict/lable_dict.py
(3) Add data_name to $PATH_ROOT/data/io/read_tfrecord.py
2、make tfrecord
cd $PATH_ROOT/data/io/
python convert_data_to_tfrecord_coco.py --VOC_dir='/PATH/TO/JSON/FILE/'
--save_name='train'
--dataset='coco'
3、multi-gpu train
cd $PATH_ROOT/tools
python multi_gpu_train.py
Eval
cd $PATH_ROOT/tools
python eval_coco.py --eval_data='/PATH/TO/IMAGES/'
--eval_gt='/PATH/TO/TEST/ANNOTATION/'
--GPU='0'
Tensorboard
cd $PATH_ROOT/output/summary
tensorboard --logdir=.
Reference
1、https://github.com/endernewton/tf-faster-rcnn
2、https://github.com/zengarden/light_head_rcnn
3、https://github.com/tensorflow/models/tree/master/research/object_detection
4、https://github.com/CharlesShang/FastMaskRCNN
5、https://github.com/matterport/Mask_RCNN
6、https://github.com/msracver/Deformable-ConvNets
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].