kaka

question about fp16

1

Warning: multi_tensor_applier fused unscale kernel is unavailable, possibly because apex was installed without --cuda_ext --cpp_ext. Using Python fallback. Original ImportError was: ModuleNotFoundError("No module named 'amp_C'") Gradient overflow. Skipping step, loss...

Question about the speed.

1

In the paper 《Objects as Points》,the running time is tested ona machine with Intel Core i7-8086K CPU, Titan Xp GPU, Pytorch 0.4.1, CUDA 9.0,and CUDNN 7.1 It gets 39.2 mAP...

coco_resnet_50_map_0_335.pt

4

I download coco_resnet_50_map_0_335.pt from https://drive.google.com/open?id=1hCtM35R_t6T8RJVSd74K4gB-A1MR-TxC ,when load using torch.load(" coco_resnet_50_map_0_335.pt") it raise error : result = unpickler.load() ModuleNotFoundError: No module named 'model' what is the problem?

In the paper "Oriented RepPoints for Aerial Object Detection Results on DOTA" , we report full experimental results of single scale to make a fair comparison with the previous methods...

Performance of yolov5m_obb on dota.

1

I use yolov5m_obb model, following the steps below: python val.py --data 'data/dotav1_poly.yaml' --img 1024 --conf 0.01 --iou 0.4 --task 'test' --batch 16 --save-json --name 'dotav1_test_split' python tools/TestJson2VocClassTxt.py --json_path 'runs/val/dotav1_test_split/best_obb_predictions.json' --save_path...

nanotrackv3.pth

1

如何对V1进行ONNX转换

run error

3

follow the procuder: git clone https://github.com/CaoWGG/TensorRT-CenterNet.git cd TensorRT-CenterNet mkdir build cd build && cmake .. && make cd .. ##cthelmet ./buildEngine -i model/ctdet_helmet.onnx -o model/ctdet_helmet.engine ./runDet -i model/ctdet_helmet.engine -img test.jpg...

error: ‘vector’ was not declared in this scope

1

enviroment: ubuntu16.04 TensorRT-5.0.2.6 How can i fix the problem?