PyTorch-YOLOv3 icon indicating copy to clipboard operation
PyTorch-YOLOv3 copied to clipboard

Minimal PyTorch implementation of YOLOv3

Results 125 PyTorch-YOLOv3 issues
Sort by recently updated
recently updated
newest added

AttributeError: module 'tensorboard.summary._tf.summary' has no attribute 'FileWriter'

How specifically can I reproduce the mAP results mentioned in readme? I have run test.py using the weights from the original darnet but only got mAP of 0.5145. How can...

I have a question about build_target function in the training process. In every yolo_layer this build_target function is called. Every yolo layer has 3 anchors and this function will find...

Traceback (most recent call last): File "train.py", line 107, in loss, outputs = model(imgs, targets) File "D:\Anaconda\Anaconda_3\lib\site-packages\torch\nn\modules\module.py", line 541, in __call__ result = self.forward(*input, **kwargs) File "D:\pytoch\PyTorch-YOLOv3-master (3)\PyTorch-YOLOv3-master\models.py", line 269,...

there is a sample imbalance problem in my data(with positive and negative ratio is 1:10),so I wanna to change the loss function to **focal loss**. anybody who knows where to...

I'm still confused about one place in **utils.py/non_max_suppression** **Line244-Line246** "" score = image_pred[ : , 4] * image_pred[ : , 5 :].max(1)[0] # Sore by it image_pred = image_pred[ (-score).argsort()...

I watch your code in evaluate. I find your NMS process all proposals bbox. It's make some trouble in early epoch due to some many remained proposals. So, I Suggest...

![image](https://user-images.githubusercontent.com/55881167/70786385-8711a780-1dc7-11ea-9f75-e3124ea04b66.png)

Traceback (most recent call last): File "D:\新建文件夹\PyTorch-YOLOv3\train.py", line 42, in logger = Logger("logs") File "D:\新建文件夹\PyTorch-YOLOv3\utils\logger.py", line 7, in __init__ self.writer = tf.summary.FileWriter(logdir) AttributeError: module 'tensorboard.summary._tf.summary' has no attribute 'FileWriter'. Why...

FileNotFoundError: [Errno 2] No such file or directory: 'data/coco/5k.txt' what should i do to solve this problem?