-
Great work! But do you have any performance result on COCO/PASCAL?
-
Hi
Can you please upload the weights that result to ultralytics yolov3 mAP reported in mAP section?
It seems like fine-tuning using those weights would be simpler than darknet pre-trained weights.
-
I try to train on open-image dataset with several diffrent ways but results are really bad.
model in detect.py, return negative anchors in some tries, or model detect nothing.
for example, I train o…
-
Hi everyone,
I have trained a custom model of 8 classes from the sl-yolov3-spp.cfg. Once I had the resulting weights, I wanted to test the mAP of the training. However, when I write the command:
…
-
I been trying to train YOLO to read image of fast food trash, but YOLO constantly makes prediction in places that doesn't really make any sense whatsoever. And the more I train, the more crazier YOLO …
-
Hi AlexeyAB,
I download the yolov3-spp.cfg from below link, and I have some question to trouble you.
1, I found that the batch=1 and subdivisons=1, is it special mean? Can I set the batch=63 and…
-
Yolov3-Tiny-XNOR
After 2K Iterations
![image](https://user-images.githubusercontent.com/31848222/54341139-1c2c1800-465f-11e9-9ca6-c5d92a3d477b.png)
After 8K Iterations
![image](https://use…
-
I noticed the log transformation of w/h offset in this repo was different from darknet as my understanding.
[utils/build_targets @Line 227](https://github.com/ultralytics/yolov3/blob/master/utils/uti…
muye5 updated
5 years ago
-
**I run demo.py, and I get an error:**
$ python3 demo.py --indir examples/demo --outdir examples/res --save_img --posebatch 1
Loading YOLO model..
THCudaCheck FAIL file=/pytorch/torch/csrc/generic…
-
I directly use the pretrained weights (yolov3.weights) to evaluate coco val2017, and get something below:
![image](https://user-images.githubusercontent.com/11806040/57613689-19d83280-75aa-11e9-9e13-…