marvis / Pytorch Yolo2
Licence: mit
Convert https://pjreddie.com/darknet/yolo/ into pytorch
Stars: ✭ 941
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Pytorch Yolo2
Yolo 9000
YOLO9000: Better, Faster, Stronger - Real-Time Object Detection. 9000 classes!
Stars: ✭ 1,057 (+12.33%)
Mutual labels: yolo, darknet, yolo2
Pytorch Caffe Darknet Convert
convert between pytorch, caffe prototxt/weights and darknet cfg/weights
Stars: ✭ 867 (-7.86%)
Mutual labels: yolo, darknet, yolo2
VideoRecognition-realtime-autotrainer-alerts
State of the art object detection in real-time using YOLOV3 algorithm. Augmented with a process that allows easy training of the classifier as a plug & play solution . Provides alert if an item in an alert list is detected.
Stars: ✭ 36 (-96.17%)
Mutual labels: yolo, darknet, yolo2
Yolov2.pytorch
YOLOv2 algorithm reimplementation with pytorch
Stars: ✭ 31 (-96.71%)
Mutual labels: yolo, darknet, yolo2
Tracking-with-darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 522 (-44.53%)
Mutual labels: yolo, darknet, yolo2
Tracking With Darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 515 (-45.27%)
Mutual labels: yolo, darknet, yolo2
Openlabeling
Label images and video for Computer Vision applications
Stars: ✭ 706 (-24.97%)
Mutual labels: yolo, darknet
darknet2caffe
Conversion of yolo from DarkNet to Caffe
Stars: ✭ 25 (-97.34%)
Mutual labels: yolo, darknet
Bmw Yolov4 Training Automation
This repository allows you to get started with training a state-of-the-art Deep Learning model with little to no configuration needed! You provide your labeled dataset or label your dataset using our BMW-LabelTool-Lite and you can start the training right away and monitor it in many different ways like TensorBoard or a custom REST API and GUI. NoCode training with YOLOv4 and YOLOV3 has never been so easy.
Stars: ✭ 533 (-43.36%)
Mutual labels: yolo, darknet
darknet ros
Robotics Operating System Package for Yolo v3 based on darknet with optimized tracking using Kalman Filter and Optical Flow.
Stars: ✭ 51 (-94.58%)
Mutual labels: yolo, darknet
object-tracking
Multiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (-90.54%)
Mutual labels: yolo, darknet
live-cctv
To detect any reasonable change in a live cctv to avoid large storage of data. Once, we notice a change, our goal would be track that object or person causing it. We would be using Computer vision concepts. Our major focus will be on Deep Learning and will try to add as many features in the process.
Stars: ✭ 23 (-97.56%)
Mutual labels: yolo, darknet
lightDenseYOLO
A real-time object detection app based on lightDenseYOLO Our lightDenseYOLO is the combination of two components: lightDenseNet as the CNN feature extractor and YOLO v2 as the detection module
Stars: ✭ 20 (-97.87%)
Mutual labels: yolo, darknet
MXNet-YOLO
mxnet implementation of yolo and darknet2mxnet converter
Stars: ✭ 17 (-98.19%)
Mutual labels: darknet, yolo2
Yolo annotation tool
Annotation tool for YOLO in opencv
Stars: ✭ 17 (-98.19%)
Mutual labels: yolo, darknet
Node Yolo
Node bindings for YOLO/Darknet image recognition library
Stars: ✭ 364 (-61.32%)
Mutual labels: yolo, darknet
pytorch-yolo2
Convert https://pjreddie.com/darknet/yolo/ into pytorch. This repository is trying to achieve the following goals.
- [x] implement RegionLoss, MaxPoolStride1, Reorg, GolbalAvgPool2d
- [x] implement route layer
- [x] detect, partial, valid functions
- [x] load darknet cfg
- [x] load darknet saved weights
- [x] save as darknet weights
- [x] fast evaluation
- [x] pascal voc validation
- [x] train pascal voc
- [x] LMDB data set
- [x] Data augmentation
- [x] load/save caffe prototxt and weights
- [x] reproduce darknet's training results
- [x] convert weight/cfg between pytorch caffe and darknet
- [x] add focal loss
Detection Using A Pre-Trained Model
wget http://pjreddie.com/media/files/yolo.weights
python detect.py cfg/yolo.cfg yolo.weights data/dog.jpg
You will see some output like this:
layer filters size input output
0 conv 32 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 32
1 max 2 x 2 / 2 416 x 416 x 32 -> 208 x 208 x 32
......
30 conv 425 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 425
31 detection
Loading weights from yolo.weights... Done!
data/dog.jpg: Predicted in 0.014079 seconds.
truck: 0.934711
bicycle: 0.998013
dog: 0.990524
Real-Time Detection on a Webcam
python demo.py cfg/tiny-yolo-voc.cfg tiny-yolo-voc.weights
Training YOLO on VOC
Get The Pascal VOC Data
wget https://pjreddie.com/media/files/VOCtrainval_11-May-2012.tar
wget https://pjreddie.com/media/files/VOCtrainval_06-Nov-2007.tar
wget https://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar
tar xf VOCtrainval_11-May-2012.tar
tar xf VOCtrainval_06-Nov-2007.tar
tar xf VOCtest_06-Nov-2007.tar
Generate Labels for VOC
wget http://pjreddie.com/media/files/voc_label.py
python voc_label.py
cat 2007_train.txt 2007_val.txt 2012_*.txt > voc_train.txt
Modify Cfg for Pascal Data
Change the cfg/voc.data config file
train = train.txt
valid = 2007_test.txt
names = data/voc.names
backup = backup
Download Pretrained Convolutional Weights
Download weights from the convolutional layers
wget http://pjreddie.com/media/files/darknet19_448.conv.23
or run the following command:
python partial.py cfg/darknet19_448.cfg darknet19_448.weights darknet19_448.conv.23 23
Train The Model
python train.py cfg/voc.data cfg/yolo-voc.cfg darknet19_448.conv.23
Evaluate The Model
python valid.py cfg/voc.data cfg/yolo-voc.cfg yolo-voc.weights
python scripts/voc_eval.py results/comp4_det_test_
mAP test on released models
yolo-voc.weights 544 0.7682 (paper: 78.6)
yolo-voc.weights 416 0.7513 (paper: 76.8)
tiny-yolo-voc.weights 416 0.5410 (paper: 57.1)
Focal Loss
A implementation of paper Focal Loss for Dense Object Detection
We get the results by using Focal Loss to replace CrossEntropyLoss in RegionLosss.
gama | training set | val set | [email protected] | [email protected] | Notes |
---|---|---|---|---|---|
0 | VOC2007+2012 | VOC2007 | 73.05 | 74.69 | std-Cross Entropy Loss |
1 | VOC2007+2012 | VOC2007 | 73.63 | 75.26 | Focal Loss |
2 | VOC2007+2012 | VOC2007 | 74.08 | 75.49 | Focal Loss |
3 | VOC2007+2012 | VOC2007 | 73.73 | 75.20 | Focal Loss |
4 | VOC2007+2012 | VOC2007 | 73.53 | 74.95 | Focal Loss |
Problems
1. Running variance difference between darknet and pytorch
Change the code in normalize_cpu to make the same result
normalize_cpu:
x[index] = (x[index] - mean[f])/(sqrt(variance[f] + .00001f));
Training on your own data
- Padding your images into square size and produce the corresponding label files.
- Modify the resize strageties in listDataset. Currently the resize scales range from 320 ~ 608, and the resize intervals is 64, which should be equal to batch_size or several times of batch_size.
- Add warm up learning rate (scales=0.1,10,.1,.1)
- Train your model as VOC does.
License
MIT License (see LICENSE file).
Contribution
Thanks for the contributions from @iceflame89 for the image augmentation and @huaijin-chen for focal loss.
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].