WilliamZhao

Results 5 issues of WilliamZhao

when I get it via env variable AZ_BATCHAI_MPI_MASTER_NODE, I get follow error File "src/scripts/submit_job/distributed.py", line 273, in set_environment_variables_for_nccl_backend os.environ['MASTER_ADDR'] = os.environ['AZ_BATCHAI_MPI_MASTER_NODE'] File "/opt/conda/lib/python3.6/os.py", line 669, in __getitem__ raise KeyError(key) from...

Is there any quantization tools for me, if I have a pretrained model with FP32, to quantize my model to a INT8 model ?

Can I get inference speed up with Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz + INT8?

thanks for your great work! I have 2 questions: 1. in make_spect_f0.py, 1). why apply a high pass filter 2). why pad a number if x.shape[0] % 256 ==0 3)....

Hi, I have a trained model in pytorch, 1. can I quantize my own model using this tool? 2. can I get acceleration when I inference the quantized model? Thanks.