-
Due to the first frame is excluded from interpolation in TimeUpsamle2x, as follows in code,
```python
x,x_= x[:,:,:1],x[:,:,1:]
x_= F.interpolate(x_, scale_factor=(2,1,1), mode='trilinear')
x = to…
-
I have trained yolov3-tiny successfully, but I want additional modification to detect bigger objects better since my data set consists of objects of various sizes. I added additional downsampling in t…
-
Hi, I've been playing with this diffusion model library for a few days, it is great to have such library that allows common users to train audio data with limited resources.
I have a problem with r…
-
Hello Mr Xuebin:
about the datasets resize method, my training image size is very big（4000*3000）, so I need to resize the image to 320*320 offline. but I compare the results of two resize method:
1…
-
on the CPC, if you type `SOUND 1,1,500,15` you hear an high pitched note but actually it should be inaudible (it's a 62 kHz tone). Same if tone is 1,2,3... (any low numbered value).
I think this is…
-
### Describe the Bug
Starting with build v1.7.5911 scaled dithering in fullscreen when cropping is broken. Causes vertical bands. Every version from v1.7.5910 and back the scaled dithering is perfect…
-
您好，我想請教一下，
我在論文中看到您計算每個 stage 的 CSPDarknet 計算量為 whb^2(9/4+3/4+5k/2) (於 4.1. CSP-ized YOLOv4 中提到)，
但在 Table 2 的比較圖中是寫 CSPDarknet 計算量為 whb^2(3/4+5k/2)，
想請問一下是我哪裡有遺漏的嗎? 謝謝您。
-
I'm trying to plot one PlotDataItem that has stepMode=True and one that has stepMode=False on same PlotItem. After that I would like to use clip to view. Is there any chance that this scenario is goin…
-
### 🐛 Describe the bug
Take the following example, I want to resize a tensor from `(941, 941)` to `(10, 10)` with `antialias=True`.
```python
import torch
from torchvision.transforms import Inte…
-
Hello everybody,
I have a dataset with 600M points and i'd like to generate a heatmap with bokeh. Do you believe it is feasible with so many points? I was looking for examples for downsampling data w…