chuanqi305 / Mobilenetv2 Ssdlite
Licence: mit
Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.
Stars: ✭ 435
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Mobilenetv2 Ssdlite
MobileNet-SSD-windows
No description or website provided.
Stars: ✭ 91 (-79.08%)
Mutual labels: caffe, ssd, mobilenet, mobilenetv2
Ssds pytorch
Multiple basenet MobileNet v1,v2, ResNet combined with SSD detection method and it's variants such as RFB, FSSD etc.
Stars: ✭ 71 (-83.68%)
Mutual labels: ssd, mobilenet, mobilenetv2
Mobilenet Ssd
Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
Stars: ✭ 1,805 (+314.94%)
Mutual labels: ssd, caffe, mobilenet
caffe-mobilenet v2
caffe based mobilenet v2 deploy
Stars: ✭ 29 (-93.33%)
Mutual labels: caffe, mobilenet, mobilenetv2
Mobilenet Caffe
Caffe Implementation of Google's MobileNets (v1 and v2)
Stars: ✭ 1,217 (+179.77%)
Mutual labels: caffe, mobilenet, mobilenetv2
Ssd Models
把极速检测器的门槛给我打下来make lightweight caffe-ssd great again
Stars: ✭ 62 (-85.75%)
Mutual labels: ssd, caffe
Tf Object Detection
Simpler app for tensorflow object detection API
Stars: ✭ 91 (-79.08%)
Mutual labels: ssd, mobilenet
Proctoring Ai
Creating a software for automatic monitoring in online proctoring
Stars: ✭ 155 (-64.37%)
Mutual labels: ssd, mobilenet
Mobilenetv3 Ssd
MobileNetV3-SSD for object detection and implementation in PyTorch
Stars: ✭ 188 (-56.78%)
Mutual labels: ssd, mobilenet
MobileNetV3-SSD-Compact-Version
MobileNetV3 SSD的简洁版本
Stars: ✭ 65 (-85.06%)
Mutual labels: ssd, mobilenet
mobilenet-v2-tensorflow
No description or website provided.
Stars: ✭ 66 (-84.83%)
Mutual labels: mobilenet, mobilenetv2
LightNet
LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)
Stars: ✭ 710 (+63.22%)
Mutual labels: mobilenet, mobilenetv2
Tensorflow Face Detection
A mobilenet SSD based face detector, powered by tensorflow object detection api, trained by WIDERFACE dataset.
Stars: ✭ 711 (+63.45%)
Mutual labels: ssd, mobilenet
Ssds.pytorch
Repository for Single Shot MultiBox Detector and its variants, implemented with pytorch, python3.
Stars: ✭ 570 (+31.03%)
Mutual labels: ssd, mobilenet
yolo3 tensorflow
yolo3 implement by tensorflow, including mobilenet_v1, mobilenet_v2
Stars: ✭ 48 (-88.97%)
Mutual labels: mobilenet, mobilenetv2
Caffe Mobilenet
A caffe implementation of mobilenet's depthwise convolution layer.
Stars: ✭ 146 (-66.44%)
Mutual labels: caffe, mobilenet
MobileNet V2 Keras
No description or website provided.
Stars: ✭ 29 (-93.33%)
Mutual labels: mobilenet, mobilenetv2
MobileNetv2-SSDLite
Caffe implementation of SSD detection on MobileNetv2, converted from tensorflow.
Prerequisites
Tensorflow and Caffe version SSD is properly installed on your computer.
Usage
- Firstly you should download the original model from tensorflow.
- Use gen_model.py to generate the train.prototxt and deploy.prototxt (or use the default prototxt).
python gen_model.py -s deploy -c 91 >deploy.prototxt
- Use dump_tensorflow_weights.py to dump the weights of conv layer and batchnorm layer.
- Use load_caffe_weights.py to load the dumped weights to deploy.caffemodel.
- Use the code in src to accelerate your training if you have a cudnn7, or add "engine: CAFFE" to your depthwise convolution layer to solve the memory issue.
- The original tensorflow model is trained on MSCOCO dataset, maybe you need deploy.caffemodel for VOC dataset, use coco2voc.py to get deploy_voc.caffemodel.
Train your own dataset
- Generate the trainval_lmdb and test_lmdb from your dataset.
- Write a labelmap.prototxt
- Use gen_model.py to generate some prototxt files, replace the "CLASS_NUM" with class number of your own dataset.
python gen_model.py -s train -c CLASS_NUM >train.prototxt
python gen_model.py -s test -c CLASS_NUM >test.prototxt
python gen_model.py -s deploy -c CLASS_NUM >deploy.prototxt
- Copy coco/solver_train.prototxt and coco/train.sh to your project and start training.
Note
There are some differences between caffe and tensorflow implementation:
- The padding method 'SAME' in tensorflow sometimes use the [0, 0, 1, 1] paddings, means that top=0, left=0, bottom=1, right=1 padding. In caffe, there is no parameters can be used to do that kind of padding.
- MobileNet on Tensorflow use ReLU6 layer y = min(max(x, 0), 6), but caffe has no ReLU6 layer. Replace ReLU6 with ReLU cause a bit accuracy drop in ssd-mobilenetv2, but very large drop in ssdlite-mobilenetv2. There is a ReLU6 layer implementation in my fork of ssd.
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].