-
Many new cfg files have been updated recently in this repository.
Can you tell me whether opencv supports them or not?
If yes, how to implements it with opencv ? Is it same with using yolov3 ?
For …
-
Hi there.
I would like to ask for an explanation regarding the onnx prediction.
As I mentioned in the title I have:
Fine-tuned YOLOv3-spp model to detect only one label (human, to be precise)…
-
Hi @WongKinYiu thanks for the great work here! I introduced new error-checking in https://github.com/ultralytics/yolov3 for custom cfgs, and after running your yolov3-spp-matrix.cfg through, I just re…
-
just as above, really thanks!!
-
## 🚀 Feature
Multi-scale testing seems to be a pretty effective trick for improve mAP.
I've implemented it on this repo, and rewrote the `detect,py`, reaching a better speed on single scale det…
-
When run
`
python detect.py --cfg cfg/yolov3-spp.cfg --weights weights/yolov3-spp.weights --img-size 608
`
error output :
```
Traceback (most recent call last):
File "detect.py", line 1…
-
In the preprint paper, I saw the difference result when test in the MSCOCO object detection task. For instance, with size 608x608 CSPResNeXt50-PANet-SPP had AP is **43.2** in the repos comparing with …
-
I tried to train with this guideline on my mac and faced this message.
unrecognized arguments: --transfer
Is there anyone who faces same problem?
-
I want to find very similar objects, but differing in small details. I need to detect it separately. Often there is confusion between them. How can I increase the recognition accuracy of these similar…
-
Be aware that `train.py` tests after each epoch at `--conf-thres 0.1` rather than the `test.py` default of `--conf-thres 0.001`. This is done intentionally to increase testing speed during training (1…