-
@AlexeyAB Hi,
Thanks for your help in advance.
I attempt to detect the varied-size people(only people) by yolov3-tiny.cfg (608x608). The **number** of people per image perhaps range from **1 to 10…
-
Hello,i'm having this error,my network size is 608x608,how can i solve this? thank you
ghost updated
4 years ago
-
-
Running the yolo example has these results.
```
./darknet detector test cfg/coco.data cfg/yolo.cfg yolo.weights data/person.jpg
layer filters size input output
…
-
I'm trying to extend a project which implements a GNN using Battaglia et al.'s definition through the `MetaLayer` class.
I would like to include some attention mechanisms as defined [here](https://g…
-
While making PR #7027 I went through the whole strings.txt file, and whenever I was confused or found something odd, I wrote it down. Some of it is noteworthy, some are just questions, and some are do…
-
I downloaded the checkpoint from the mentioned link: https://drive.google.com/open?id=0B1l5JSkBbENBdk95ZW1DOUhqQUE
When i run the command: python cam.py --model_path cam_checkpoint.hdf5 --image_pat…
-
Hi @AlexeyAB,
After training successfully the yolo3 model for custom objects we have been testing the prediction and we have found out that the biggest scale (anchors 6,7,8 or downsample by 8) is n…
-
Hi
I'm training a tiny yolov2 to detect 4 classes.
Without setting random=1, I'm getting an IOU of around 57% and a mAP of around 58% on my validation set. The region average IOU of the subdivis…
-
