pytorch-yolo-v3

pytorch-yolo-v3 copied to clipboard

In my subjects,I find a problems during the person detect,that exist false retrieval.

2

 As you see in the images,The detected object is false,How can i improving this false performance.

Ronales

just train person

1

how should i do if just train and test person?i wanna to train a person detector.thks

shayxurui

I have a stronger yolo

3

I have a better code about yolo https://github.com/Stinky-Tofu/Stronger-yolo

Stinky-Tofu

only test people

2

I want to test only people. What should I do? thank you

kclch

Cuda 10 is installed ,and was properly working while back. But now its showing this error. THCudaCheck FAIL file=..\aten\src\THC\THCGeneral.cpp line=87 error=30 : unknown error how to solve this?

Achuth07

Hi, Thank you so much for your code. I am using your code for object detection in videos. But for some of the input video, the code stops working. what...

manza-ari

Hi, Thank you so much for sharing your code. how to resolve this error: output[:,[1,3]] -= (inp_dim - scaling_factor*im_dim[:,0].view(-1,1))/2 RuntimeError: invalid argument 2: input is not contiguous at /pytorch/torch/lib/THC/generic/THCTensor.c:227

manza-ari

use interpolate instead of upsample?

1

Hello i am trying to implement it also in pytorch following your code.. Do you know how can i change the process of the upsample nn.Module created to use interpolate...

richipower

creating picture of objects detected

1

is there a way to create a file with pictures of all objects that have been detected in a video? I tried tweaking the code but I did not get...

aRealBanana

Segmentation Fault (Core Dumped) Thanks!!!

1

Hi, I am a big fan of your work. And I try to simply test your code before I start following your tutorial. However, when I cd to where I...

mylife126