使用transformer的YOLOv7及TensorRT部署
使用transformer的YOLOv7及TensorRT部署
最近在github上看到一个博主开源的YOLOv7仓库都惊呆了，YOLOv6都还没出来怎么就到YOLOv7了
稍微看了下，原来作者是基于这两年来很火的transformer做的检测和分割模型，测试的效果都非常棒，比YOLOv5效果好很多。由此可见，基于Transformer based的检测模型才是未来。你会发现它学到的东西非常合理，比从一大堆boudingbox里面选择概率的范式要好一点。话不多说，先上代码链接：
https://github.com/jinfagang/yolov7
开源的YOLOv7功能很强大，支持 YOLO, DETR, AnchorDETR等等。作者声称发现很多开源检测框架，比如YOLOv5、EfficientDetection都有自己的弱点。例如，YOLOv5实际上设计过度，太多混乱的代码。更令人惊讶的是，pytorch中至少有20多个不同版本的YOLOv3-YOLOv4的重新实现，其中99.99%是完全错误的，你既不能训练你的数据集，也不能使其与原paper相比。所以有了作者开源的这个仓库！该repo 支持DETR等模型的ONNX导出，并且可以进行tensorrt推理。
该repo提供了以下的工作：
- YOLOv4 contained with CSP-Darknet53;
- YOLOv7 arch with resnets backbone;
- GridMask augmentation from PP-YOLO included;
- Mosiac transform supported with a custom datasetmapper;
- YOLOv7 arch Swin-Transformer support (higher accuracy but lower speed);
- RandomColorDistortion, RandomExpand, RandomCrop, RandomFlip;
- CIoU loss (DIoU, GIoU) and label smoothing (from YOLOv5 & YOLOv4);
- YOLOv7 Res2net + FPN supported;
- Pyramid Vision Transformer v2 (PVTv2) supported
- YOLOX s,m,l backbone and PAFPN added, we have a new combination of YOLOX backbone and pafpn;
- YOLOv7 with Res2Net-v1d backbone, we found res2net-v1d have a better accuracy then darknet53;
- Added PPYOLOv2 PAN neck with SPP and dropblock;
- YOLOX arch added, now you can train YOLOX model (anchor free yolo) as well;
- DETR: transformer based detection model and onnx export supported, as well as TensorRT acceleration;
- AnchorDETR: Faster converge version of detr, now supported!
仓库提供了快速检测Quick start和train自己数据集的代码及操作流程，也提供了许多预训练模型可供下载，读者可依据自己的需要选择下载对应的检测模型。
快速运行demo代码
python3 demo.py --config-file configs/wearmask/darknet53.yaml --input ./datasets/wearmask/images/val2017 --opts MODEL.WEIGHTS output/model_0009999.pth
实例分割
python demo.py --config-file configs/coco/sparseinst/sparse_inst_r50vd_giam_aug.yaml --video-input ~/Movies/Videos/86277963_nb2-1-80.flv -c 0.4 --opts MODEL.WEIGHTS weights/sparse_inst_r50vd_giam_aug_8bc5b3.pth
基于detectron2新推出的LazyConfig系统，使用LazyConfig模型运行
python3 demo_lazyconfig.py --config-file configs/new_baselines/panoptic_fpn_regnetx_0.4g.py --opts train.init_checkpoint=output/model_0004999.pth
训练数据集
python train_net.py --config-file configs/coco/darknet53.yaml --num-gpus 1
如果你想训练YOLOX，使用 config file configs/coco/yolox_s.yaml
导出 ONNX && TensorRT && TVM
detr
python export_onnx.py --config-file detr/config/file
SparseInst
python export_onnx.py --config-file configs/coco/sparseinst/sparse_inst_r50_giam_aug.yaml --video-input ~/Videos/a.flv --opts MODEL.WEIGHTS weights/sparse_inst_r50_giam_aug_2b7d68.pth INPUT.MIN_SIZE_TEST 512
具体的操作流程可以去原仓库看，都有详细的解析！
检测结果
参考链接
[1]https://manaai.cn/aisolution_detail.html?id=7
[2]https://github.com/jinfagang/yolov7