Cw-zero / TensorRT_yolo3
use TensorRT accelerate yolo3
☆122Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for TensorRT_yolo3
- You can import this module directly☆55Updated 5 years ago
- TensorRT for Yolov3☆49Updated 5 years ago
- ☆44Updated 5 years ago
- ☆79Updated 5 years ago
- Convert YOLOv3 and YOLOv3-tiny (PyTorch version) into TensorRT models.☆61Updated 4 years ago
- convert your yolov3-tiny model to trt model☆90Updated 4 years ago
- c++ version of https://github.com/nwojke/deep_sort.☆143Updated 4 years ago
- Darknet2ncnn converts the darknet model to the ncnn model☆158Updated 4 years ago
- provide pytorch model and ncnn model☆77Updated 4 years ago
- 重新设计的RFBNet300,模型参数量只有0.99MB,AP达到0.78,200FPS☆99Updated 4 years ago
- Accelerate mobileNet-ssd with tensorRT☆187Updated 5 years ago
- Run YoloV3 with the newest TensorRT6.0 at 37 fps on NVIIDIA 1060.☆86Updated 4 years ago
- TensorRT Net Wrapper☆95Updated 5 years ago
- A keras version of real-time object detection network : mobilenet_v2_ssdlite☆80Updated 4 years ago
- This is the unofficial implementation of the "CenterNet:Objects as Points".Just a simple try with self-modified shufflenetv2 and yolov3.…☆111Updated 3 years ago
- Object detection model thundernet tensorflow.keras implementation☆83Updated 5 years ago
- darknet2onnx2tensorrt☆26Updated 5 years ago
- ☆67Updated 4 years ago
- ☆237Updated 5 years ago
- ☆29Updated 5 years ago
- MobileNetV3 based SSD-lite implementation in Pytorch☆98Updated 5 years ago
- YOLOv3-training-prune☆59Updated 3 years ago
- Caffe: a fast open framework for deep learning.☆38Updated 6 years ago
- 设计的轻量级RFB进行行人检测,AP达到0.7993,参数量仅有3.1MB,200 FPS☆174Updated 4 years ago
- MNN demo of Strongeryolo, including channel pruning, android support...☆105Updated 5 years ago
- Integrate SlimYoloV3 in YOLOv3 in PyTorch in Branch slimyolov3☆26Updated 5 years ago
- ☆33Updated 5 years ago
- YOLO V2 & V3 , YOLO Combined with RCNN and MaskRCNN☆115Updated 4 years ago
- 基于CenterNet训练的目标检测&人脸对齐&姿态估计模型☆282Updated 3 years ago