PyTorch-YOLOv3

PyTorch-YOLOv3 copied to clipboard

RuntimeError: CUDA error: an illegal memory access was encountered

1

Happens here: ```class_mask[b, best_n, gj, gi] = (pred_cls[b, best_n, gj, gi].argmax(-1) == target_labels).float()``` in utils file. My env: Python 3.7.3 Pytorch 1.0.0 Cudatoolkit 10.1.168 Windows 10 i5 cpu and 4gb...

sholalkere

convert this project's .pth to darknet's .weights

8

I want to convert this project's .pth to darknet's .weights ,anyone else have some advice? I try to load .pth to model, and then save modle's para to .weights ,...

LifeIsSoSolong

detect.py : how to use the code to have detections on a custom trained YOLO

2

I noticed that there are a lot of people (#196, #168, #111, #86, #64, #55) that don't have detection's with a custom trained YOLO. I had the same problem. I...

pieterblok

Testing: different mAP for different batch sizes

6

Hi, thanks a lot for the repo ) I have encountered a problem that testing with the different batch size gives different mAP. For instance: batch_size = 1: mAP =...

AlexGrig

Not able to reproduce the mAP results after training

16

Thank a lot for producing this amazing code! I am training to train yolov3 on coco After preprocessing the dataset, I ran `` python3 train.py --data_config config/coco.data --pretrained_weights weights/darknet53.conv.74 ``...

gurkirt

Why did my test only achieve mAP: 0.409?

28

I tried the `python test.py --weights_path weights/yolov3.weights`, but get mAp: 0.409

CS-Jackson

train on voc problem

9

When I train on voc, it shows: Traceback (most recent call last): File "1train.py", line 60, in model = Darknet(opt.model_config_path) File "/public/home/G19850028/zheng/workspace/yolo-erik/models.py", line 241, in __init__ self.yolo_layers = [layer[0] for...

loneclown

VOC train

1

I want to train on VOC dataset.The train parts are voc2007_train and voc2012_trian, The Validation parts are voc2007_val and voc2012_val.Is right?How ablout map?Thank you.

risemeup

Anyone has trained voc dataset succussfully?

2

Hello, I have trained VOC dataset for more than 100 epochs, but got poor mAP like follow picture, could you give me some advice? ``` 61 0.385491111925769 +-------+-------------+---------+ | Index...

ArtyZe

average precision larger than 1

1

during evaluation, ap for one of the target classes gets better than 1, like 1.76, how is this possible? is there anything i'm missing from using the code?

flyfj