980202006

Results 48 issues of 980202006

I want to split a single npy file read by fn.readers.numpy in 100-bit units according to the first dimension, is there any function available?

help wanted

I want to train the vocoder on my own data set. Is there any suggestion on the amount of data to converge, as well as the training time, and the...

Hi,I use one machine with 5 2080ti. On training, the steps dose not crease when it is 10. ![image](https://user-images.githubusercontent.com/24452502/115810088-e4882080-a41f-11eb-8b63-d25a8eaf36c7.png) Loss normal decline.

The problem doesn't exist when I run paddleocr alone, but if I load the torch model, the problem occurs. ``` Traceback (most recent call last): File "/home/xingyum/anaconda3/envs/vis/lib/python3.10/runpy.py", line 196, in...

## Description Set_binding_shape returns False ``` import os import sys sys.path.append(os.path.abspath(os.path.dirname(os.path.dirname(__file__)))) import os.path import numpy as np from multiprocessing import cpu_count import cv2 import shutil from PIL import Image from...

triaged

There is int type data in my inputs for indexing other data, how can I set the int type data as input, with set_input?

triaged

## Description [08/04/2022-17:24:38] [TRT] [V] *************** Autotuning Reformat: Float(E8,E8,E7,E6,(* 108 E1),108,1) where E0=(- 108 (- (# 3 (SHAPE input_1)) (* 108 (CEIL_DIV (+ (# 3 (SHAPE input_1)) -107) 108)))) E1=(CEIL_DIV...

triaged

There is no torch.nonzero in my torch model, but a nonzero error is reported. Which torch operations may cause nonzero problems, or how can I find out which operators contain...

wontfix
triaged

would this model be available on videos ?

I tried run_speech_classification_example.py for speech sentiment classification data, but only got acc of 0.16. How to improve the accuracy rate? ![image](https://user-images.githubusercontent.com/24452502/168718861-03d78c36-f5ff-4794-a6d4-ac020a363e3a.png)