leayz-888

RuntimeError: "ms_deform_attn_forward_cuda" not implemented for 'Half'

1

When I try to use mixed precision training, the program reports an error: Traceback (most recent call last): File "main.py", line 414, in main(args) File "main.py", line 335, in main...

predict, ValueError:not enough values to unpack (expected 2, got 1)

1

First of all, thank you for your great work! I want to use a lama-fourier model trained on the places dataset to make predictions on my own dataset, the command...

end2end C++推理报错，[pluginV2DynamicExtRunner.cpp::execute::115] Error Code 2: Internal Error (Assertion status == kSTATUS_SUCCESS failed. )

15

您好，我按照指令:python export.py --weights ./yolov7-tiny.pt --grid --simplify将pt模型转为onnx 然后使用:python export.py -o ./yolov7-tiny.onnx -e yolov7-tiny.engine -p int8 --calib_input ./calibration_img --end2end --calib_num_images 500 进行量化，成功得到了engine文件，但是我发现engine文件有7个输出，分别是：278/336/394、num/boxes/scores/classes，前面3个是小、中、大检测头的输出，后4个是端到端的输出，我确认了main.cpp中的输入输出节点名称是一样的，但是在使用engine文件推理的时候报错: [pluginV2DynamicExtRunner.cpp::execute::115] Error Code 2: Internal Error (Assertion status == kSTATUS_SUCCESS...

大佬您好，请问一下为什么我使用您的代码做int8量化的时候，量化过程不稳定呢？比方说，我这一次量化可以得到好的量化模型，但是同样的模型，同样的代码，没有改动任何地方，下次量化模型的精度就不行了。我想请问一下为什么会有这种随机性呢？

The inference results of the pretrained models yolov7.pt and yolov7.trt are inconsistent

3

I tested some images of the coco validation set and got the following test results: Inference result of yolov7.pt:  Inference result of yolov7.trt(fp16):  Inference result of yolov7.trt(fp32): ...

RuntimeError: shape '[32, 66, -1]' is invalid for input of size 29491200

13

### Search before asking - [x] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/orgs/ultralytics/discussions) and found no similar questions. ### Question Hi,nice job!When I use the following script to...

非常棒的工作！请问一下重参数化微调过程中，不需要语言模型了，是否不能加入GQA数据一起训练呢？