-
The original darknet learning rate (LR) scheduler parameters are set in a model's *.cfg file:
- `learning_rate`: initial LR
- `burn_in`: number of batches to ramp LR from 0 to `learning_rate` in epo…
-
### Search before asking
- [X] I have searched the YOLOv5 [issues](https://github.com/ultralytics/yolov5/issues) and [discussions](https://github.com/ultralytics/yolov5/discussions) and found no simi…
-
## 🐛 Bug
when i try to train ,it tell me can not find a file named test.shape...
how can i get it ?
D:\anaconda\envs\pytorch\python.exe D:/Py_Program/yolov3-master/train.py
Namespace(accumulate=…
-
First of all, thank you for the hard work and the great documentation. Can you help with this error? It occurs upon calculation of the mAP and appears related to an opencv rendering. I have 4 classes …
-
## 🐛 Bug
## To Reproduce (REQUIRED)
Model type: Object detection model
Select model: baseline-yolo5
Batch size: 8, Epoch: 80, H/W: 128x128
Input:
```
mlp.train_yolov5(
exp_name.value…
-
Help~ in ultralytics/yolov3 i use
python3 ./train.py --cfg cfg/yolov3-spp3.cfg --weights weights/darknet53.conv.74 --data data/collector.data --epochs 30
will error
File "/root/projects/yolov3/…
-
## 🐛 Bug
Thank you for sharing your project !!!
Training custom data which has two classes, if I don't modify the filtersize and numclasses in '.cfg' file, everything works fine, I can train and det…
-
Input:
```
!python3 detect.py --classes 0
#!python3 detect.py --cfg cfg/yolov3-tiny.cfg --weights yolov3-tiny.pt --classes 0
```
Output:
```
Namespace(agnostic_nms=False, augment=False…
-
## ❔Question
Hiya! Thank you for your contribution. I have trained YOLOv3-spp on my own dataset and the test result on the validation set is very good ofc. However, the results on the test set revea…
-
https://github.com/luizgh/sigver_wiwd/blob/3e509df4cebc5d8dbb083373a017e7d0cea4f0be/signet_spp_300dpi.py#L19
As shown in your paper "Table 1", this pooling layer is defined as "pool3-s2-p0", as suc…