wsy-yjys

```bash (py39torch2) wsy@ubuntu:~/paper2/mmyolo$ python tools/analysis_tools/benchmark_old.py configs/yolov6/yolov6_v3_n_syncbn_fast_2xb32-300e_coco_SGD.py work_dirs/yolov6_v3_n_syncbn_fast_2xb32-300e_coco_SGD/best_coco_bbox_mAP_epoch_300.pth --fuse-conv-bn --max-iter 20 --repeat-num 3 --task inference usage: benchmark_old.py [-h] [--repeat-num REPEAT_NUM] [--max-iter MAX_ITER] [--log-interval LOG_INTERVAL] [--work-dir WORK_DIR] [--fuse-conv-bn] [--cfg-options CFG_OPTIONS [CFG_OPTIONS ...]]...

@slantingsun Hello, mmyolo does not have task arguments. In addition, I tested other models, including yolox and yolov7, and their fps is normal, only yolov6_v3 is abnormal.

@slantingsun, your test is yolov5, I use the following command, yolov6_v3_n_syncbn_fast results are still abnormal, have you tested yolov6？ ```bash (py39torch2) wsy@ubuntu:~/paper2/mmyolo$ mim run mmdet benchmark configs/yolov6/yolov6_v3_n_syncbn_fast_2xb32-300e_coco_SGD.py --checkpoint work_dirs/yolov6_v3_n_syncbn_fast_2xb32-300e_coco_SGD/best_coco_bbox_mAP_epoch_300.pth --fuse-conv-bn...

@Le0v1n What is `meta info` , how to add it, and is there any documentation?

可以具体说说吗，怎么实现？

This is my torch and torchvision version ```bash torch 1.8.0+cu111 torchvision 0.9.0+cu111 ```

ok, thank you~

```bash RuntimeError: CUDA error: no kernel image is available for execution on the device ``` Hi, I meet a new problem, is these means what?

>/pytorch/aten/src/ATen/native/cuda/Loss.cu:102: operator(): block: [301,0,0], thread: [60,0,0] Assertion `input_val >= zero && input_val = zero && input_val = zero && input_val = zero && input_val

Another question about the batch size, when I reduce the bacth size, does the learning rate need to be reduced correspondingly, thank you~