Ghustwb / Mobilenet Ssd Tensorrt
Accelerate mobileNet-ssd with tensorRT
Stars: ✭ 183
Labels
Projects that are alternatives of or similar to Mobilenet Ssd Tensorrt
Image Quality Assessment
Convolutional Neural Networks to predict the aesthetic and technical quality of images.
Stars: ✭ 1,300 (+610.38%)
Mutual labels: mobilenet
Mobilenet
A Clearer and Simpler MobileNet Implementation in TensorFlow
Stars: ✭ 119 (-34.97%)
Mutual labels: mobilenet
Posenet Coreml
I checked the performance by running PoseNet on CoreML
Stars: ✭ 143 (-21.86%)
Mutual labels: mobilenet
Tf Object Detection
Simpler app for tensorflow object detection API
Stars: ✭ 91 (-50.27%)
Mutual labels: mobilenet
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (-36.61%)
Mutual labels: mobilenet
Tensorflow realtime multi Person pose estimation
Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3
Stars: ✭ 129 (-29.51%)
Mutual labels: mobilenet
Tf Mobilenet V2
Mobilenet V2(Inverted Residual) Implementation & Trained Weights Using Tensorflow
Stars: ✭ 85 (-53.55%)
Mutual labels: mobilenet
Pytorch Cifar100
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)
Stars: ✭ 2,423 (+1224.04%)
Mutual labels: mobilenet
Faster Mobile Retinaface
[CVPR 2020] Reimplementation of RetinaFace, faster and stronger.
Stars: ✭ 117 (-36.07%)
Mutual labels: mobilenet
Mobilenet Ssd
Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.
Stars: ✭ 1,805 (+886.34%)
Mutual labels: mobilenet
Face landmark dnn
Face Landmark Detector based on Mobilenet V1
Stars: ✭ 92 (-49.73%)
Mutual labels: mobilenet
Libgdl
一个移动端跨平台的gpu+cpu并行计算的cnn框架(A mobile-side cross-platform gpu+cpu parallel computing CNN framework)
Stars: ✭ 91 (-50.27%)
Mutual labels: mobilenet
Efficientnet
Implementation of EfficientNet model. Keras and TensorFlow Keras.
Stars: ✭ 1,920 (+949.18%)
Mutual labels: mobilenet
Rfbnet
Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018
Stars: ✭ 1,272 (+595.08%)
Mutual labels: mobilenet
Object Localization
Object localization in images using simple CNNs and Keras
Stars: ✭ 130 (-28.96%)
Mutual labels: mobilenet
Proctoring Ai
Creating a software for automatic monitoring in online proctoring
Stars: ✭ 155 (-15.3%)
Mutual labels: mobilenet
Caffe Mobilenet
A caffe implementation of mobilenet's depthwise convolution layer.
Stars: ✭ 146 (-20.22%)
Mutual labels: mobilenet
Paddlex
PaddlePaddle End-to-End Development Toolkit(『飞桨』深度学习全流程开发工具)
Stars: ✭ 3,399 (+1757.38%)
Mutual labels: mobilenet
MobileNet-SSD-TensorRT
To accelerate mobileNet-ssd with tensorRT
TensorRT-Mobilenet-SSD can run 50fps on jetson tx2
Requierments:
1.tensorRT4
2.cudnn7
3.opencv
Run:
cmake .
make
./build/bin/mobileNet
Reference:
https://github.com/saikumarGadde/tensorrt-ssd-easy
https://github.com/chuanqi305/MobileNet-SSD
I replaced depthwise with group_conv,because group_conv has been optimized in cudnn7
I retrianed mobileNet-SSD,my number of classfication is 5
TODO:
- [x] To save serialized model
- [x] To solve the bug of getting different result with same input
- [ ] The bottleneck of time cost lies in the decoding of pictures. "imread" cost too much ,to resolve it.
- [x] To modify the architecture, decrease the time cost
If want to decrease the time cost of "imread",you could rebuild OpenCV[https://github.com/jetsonhacks/buildOpenCVTX2]
Added producer-consumer
The bug has been fixed
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].