keras-yolo3

keras-yolo3 copied to clipboard

why "h,w = input_shape" is not "w,h = input_shape" ?

1

https://github.com/qqwweee/keras-yolo3/blob/e6598d13c703029b2686bc2eb8d5c09badf42992/train.py#L140

Atakey

input_shape

1

hello! I want to change model_image_size in yolo.py to 768,768. Do I need to modify input_shape to 768,768 in train.py at the same time? I tried it. After training the...

tangbinbinyes

Layer shape mismatch when loading pretrained weight when using Keras included in Tensorflow

1

I wanted to load YOLOv3 model and retrain it using provided pre-trained model. I got stuck for a while on this error : `ValueError: Layer #1 (named "conv2d_1"), weight has...

Nakeuh

yolo_video.py RuntimeError: The Session graph is empty

1

I download the code and want to learn about it. I convert .weights to .h5 and then I run yolo_video.py. I get the error: RuntimeError: The Session graph is empty...

github2016-yuan

问一下大佬们，这个代码测试视频的时候能达到多少FPS？

8

lofyol

I want to continue to use the existing pretrained models with an extra object-helmet. How do I do this?

sriramcu

Used to modify the H coordinate after flipping the picture

KaiserChoi

"image_shape:01 is disconnected" error on model conversion to ONNX

1

I am trying to convert the YOLOv3 model here to ONNX. This is also crossposted to the keras-onnx repository (https://github.com/onnx/keras-onnx/issues/606), but I wanted to post it here for outreach as...

semihcanturk

about loss function:confidence_loss

4

Keras-yolo3/yolo3/model.py line 401 **confidence_loss = object_mask * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True)+ (1-object_mask) * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True) * ignore_mask** I want to know what **(1-object_mask) * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True) * ignore_mask** mean。...

jinbooooom

why box_xy in a normalization model should minus the offset between the recovery image shape and compress origin image?

2

This is a issue when I read the definition of yolo_head and yolo_correct_boxes in the model.py. In previous, the function of the box_xy: box_xy = (K.sigmoid(feats[..., :2]) + grid) /...

QuntuamLoop