-
I build a model and yolov3 is part of it. The picture of losses is below:
![image](https://user-images.githubusercontent.com/11806040/59606687-5ae0db00-9144-11e9-920f-3d207514751d.png)
As you can s…
-
**Describe the bug**
I used 1024*288 images as a training image, using four 1080ti gpus. I tried to enable both rectangular_training and multi-scale_learning but tensor size mismatch occurred on rou…
-
Hi,
Thanks for the awesome work! I've been training using default setting and now is in epoch 241 with the result below (Fig. 1). I have some inquires below.
1. Is the result you report [here](https…
-
Hi , i have some question, Alphapose result on coco is good, your group said pytorch-version can achieves 71mAp on COCO dataset. Is this result producted by the "yolov3-spp.weights(from darknet pretra…
-
Hi,
I am trying to use the default yolov3.weights and yolov3.cfg. I came across this strange observation of different bflops and hence different fps while running object detection using `darknet_vide…
-
Hi,
How to understand the difference between
[yolov3-tiny.cfg](https://github.com/AlexeyAB/darknet/blob/master/cfg/yolov3-tiny.cfg) and [yolov3-tiny_3l](https://github.com/AlexeyAB/darknet/blob/mas…
-
@AlexeyAB hi!!!
I am training my own dataset with only one class. Dataset contains of **1k** labeled images and **1k** unlabeled(empty .txt file). Each images contains from 1 to 600 small objects.
…
-
I have been testing the speed of my custom trained yolov3-tiny with 4 classes, on a 2080ti (Turing) and a Xavier (Volta). However using xnor or INT8 both have
JC-13 updated
5 years ago
-
Thanks for your project. I have tested it successfully, but I have something wrong during the training. The information is as follows. Can you give some suggestions?
python train.py
Namespace(accumu…
-
Hi,
I would like to know if you had issues for tracking when a robot is following because, at least to me, the transform keeps jumping position from close to far as if there is no filter or somethi…