-
The code just find the best gt_box over 0.5IoU assign to each anchor, if there have gt_boxes can't find any anchor matched over 0.5IoU, those gt_boxes may not be trained. Briefly, does Bipartite Match…
-
If you have any ideas for improving yolo, you can come up here.
-
Thank you for the great work,
my question is: is it possible to use YOLO3 to differentiate between persons standing, laying and sitting? and what is your recommendations for the cfg file? i did some…
-
yolov4在darknet下训练mAP能达到90%以上，这里稀疏训练-s设为0.0006，第三个epoch就map变成0，即使直接基础训练，第3个epoch后 所有指标就都变为0，train_batch0.jpg 和test_batch0.jpg显示也正常。后面用yolov3-spp重头开始训练自己的训练集，以下四个指标也一直是0，想请教一下问题可能出在哪里
```
Class Im…
-
Hi,
I'm running the same cfg file on the same setup on Windows 10 and PopOs 19.10 and finding that linux runs much faster than Windows 10. Is there a reason for this or a way that I can fix my Wind…
-
Hi,
I would like to train yolo3-spp with other resolutions, like 416 and 832 (Default = 608).
In this case, would it be necessary to change the size of the maxpool filters (Default = 5, 9 and 13)?…
-
Hey @AlexeyAB I was wondering if you had any tips for decreasing the video memory footprint of darknet without decreasing the network size or changing the cfg? I have a 2080Ti and I'm using libdarknet…
-
in the cfg file, the first shortcut layer cut is from -4, which is convolutional layer with filters=64, while the convolutional layer before this [shortcut] is filters=128, they cannot be added, is th…
-
I added Self-adversarial training.
How to use:
```
[net]
adversarial_lr=1
#attention=1 # just to show attention
```
Note for **Classifier**: it seems it makes training unstable for high lear…
-
How can I found or build build_utils.py? Could you just give me a demo? Or could you please clarify the meaning of the functions and variables in build_utils.py?
ZrW00 updated
2 years ago