delldu

icon company Vision icon location ShenZhen,China icon location Embedded, CV and NLP Senior Engineer.

Results 16 comments of delldu

[Bug] nn.Conv2d is not a generic kernel, it works only for specific numbers of channels.

examples/08_esrgan same situation `$ python compile.py --model-path RealESRGAN_x4plus.pth ` File "/media//8t/Workspace/study/AITemplate/python/aitemplate/backend/cuda/conv2d/common.py", line 805, in gen_function emitted_instance = f_emit_instance(op_instance[value]) KeyError: ''

[Bug] nn.Conv2d is not a generic kernel, it works only for specific numbers of channels.

examples/01_resnet-50 `$ python infer_with_torch.py ` File "/media//8t/Workspace/study/AITemplate/python/aitemplate/backend/cuda/conv2d/common.py", line 805, in gen_function emitted_instance = f_emit_instance(op_instance[value]) KeyError: ''

[Bug] nn.Conv2d is not a generic kernel, it works only for specific numbers of channels.

examples/01_resnet-50 `$ python benchmark_ait.py` File "/media/8t/Workspace/study/AITemplate/python/aitemplate/backend/cuda/conv2d/common.py", line 805, in gen_function emitted_instance = f_emit_instance(op_instance[value]) KeyError: ''

How do pixel unshuffle in ggml ?

Thanks@ggerganov , we tested, the answer is not correct.

Questions on the shared pretrained model

Oh MY God !!! 1) Code does not match the paper 2) Effect does not match the paper (pre-trained model performance too bad) 3) Run time does not match the...

video support

Good luck for you !!! In my opinion, applying ggml on **video(AI)** may be nightmare, because it dose not support tensor more than 4d, so conv3d, batchnorm3d etc will make...