Chen Xupeng

--clear --all 会删除整个课程

2

使用--clear --all命令的时候发现几十个课程的文件夹都被直接删除了，似乎是个bug？

frontend_to_onnx raised an issue

2

**Describe the issue**: Hi, I am using nni for model quantization. When I do modelspeedup using ``` engine = ModelSpeedupTensorRT(model, input_shape, config=calibration_config, batchsize=batch_size) ``` It raised an error `TypeError: The...

where is scripts.compression_mnist_model

3

**Describe the issue**: When I tried to run the demo from the doc here https://nni.readthedocs.io/en/stable/tutorials/quantization_speedup.html, I could not found `scripts.compression_mnist_model` in `from scripts.compression_mnist_model import TorchModel, trainer, evaluator, device, test_trt` **Environment**:...

how to control upsample scales

12

I use the default setting of [4,4,4,4] in 20180510_mixture_lj_checkpoint_step000320000_ema.json for umsample parameters, and I got an error from ``` if c is not None and self.upsample_net is not None: c...

Hey, I am trying to run the codes in NB4b - Alternative Model (Training), I found the `DATA_PATH = f'data/{notebook_name}/'` but the data is not provided? I am not sure...

RuntimeError: CUDA error: no kernel image is available for execution on the device

1

Hi, thanks for the codes! I run into a problem when executing: ``` import torch from performer_pytorch import Performer model = Performer( dim = 512, depth = 1, heads =...

f0 estimation in silent period

3

Hi, I have a question when I use CREPE to estimate f0 in human voice dataset. I found that the f0 has fluctuation even in audio's silent period. Is it...

好像没有windows version？

1

windows的软件似乎没法下载了？

Hi, thanks for the great codes! Just wondering if you have any plan to support the 3D version of SimMIM (Video Swin Masked Encoding)? I think there is some paper...

change frame rate of estimated pitch

8

hey, I am also trying to use SPICE to estimate f0, but I found the model in tf hub did not allow me to change the frame rate of the...