Taha Azzim comments

Repositories
Issues
Comments

Results 5 comments of


                                            Taha Azzim

Internal Error (Assertion min_ <= max_ failed.)

Try `IInt8MinMaxCalibrator` instead of `IInt8EntropyCalibrator`

Internal Error (Assertion min_ <= max_ failed.)

Another thing you may want to check is the calibration file of the `int8_calibrator`. Make sure there's no previous file with the same name, if so, remove it first.

fp16 engine works fine with trtexec but encountering nan with python API

happened to me because of the model weights, some were smaller than fp16 min value. those weigths are clamped to zeros, then because of some zeros divisions, nans appear. To...

Are torch.nn.functional methods automatically quantized by pytorch-quantization?

add `quant_modules.initialize()`

Cask (shader run failed)

@DaraOrange for nms, you can replace the operation with this https://github.com/meituan/YOLOv6/blob/d512ce7c4f103e8887960198505518bed404abdc/yolov6/models/end2end.py#L235