keras-yolo3

keras-yolo3 copied to clipboard

How do you test model on data?

1

I trained YOLOv3. How do I get metric results on my test dataset? It is on images.

brian123214

AttributeError: 'str' object has no attribute 'decode'

3

运行train.py时出现错误

cutelyy123

File "/home/liyuewen/PycharmProjects/keras-yolo3-master/yolo3/utils.py", line 39, in get_random_data image = Image.open(line[0]) IndexError: list index out of range

3

li829

TypeError: unicode argument expected, got 'str'

7

Using TensorFlow backend. Loading weights. ('Weights Header: ', 0, 2, 0, array([32013312])) Parsing Darknet config. Traceback (most recent call last): File "convert.py", line 262, in _main(parser.parse_args()) File "convert.py", line 83,...

hejie

Hello, I have a custom yolov3 model with width=960 and height=512 and the convert.py is converting my model to 416x416 any ideas on how to keep my custom width and...

pteran2403

Yolo3 make error

1

tried to build yolo3 model with the instructions of here. https://pjreddie.com/darknet/yolo/ . but when i change my make file for GPU configuration as follows and set all the paths in...

ShanakaRG

yolo v3中文交流

351

脑子一热，想开个中文帖。自己对qwe大神的keras-yolo3代码已经研读过一段时间，并且有一些收获和总结。大家有什么问题想中文交流的可以在下面提出来，用母语交流比较方便，我尽可能解决大家的问题。 同时，希望在这里能遇到跟我做相同研究的Chinese ^ o^，互相交流互相提升。 我关于yolo v3的总结写了一篇中文blog，希望对大家理解这个版本的yolo3有所帮助 https://blog.csdn.net/leviopku/article/details/82660381 需要进一步交流的，可以联系我的邮箱: [email protected]

leviome

> 你好，我训练自己的数据集，win10+navida 3090+python3.6；执行train.py后，loss一直是nan，如何解决？请教指导，谢谢。 请问你的训练环境是tf1还是tf2，训练数据有没有进行数据增强？ _Originally posted by @OMPC0 in https://github.com/qqwweee/keras-yolo3/issues/254#issuecomment-1010826119_

junlintianxiatjm

Facing issue while converting Darknet YOLO model to keras model

1

I was trying to convert A Darknet YOLO model to keras model using convert.py file. using the following command: ```python3 convert.py yolov3.cfg yolov3.weights model_data/yolo.h5``` the command gives following output and...

ketan9808

IndexError: index 160 is out of bounds for axis 0 with size 160

4

I get this error when I train on bottleneck. IndexError: index 160 is out of bounds for axis 0 with size 160 This is the code that the error says...

ShimaShamli