YAD2K

YAD2K copied to clipboard

Greetings! Hopefully, someone would be able to help me understand the difference between yad2k.py vs keras_yolo.py. On the onset, it seems like yad2k.py reads Darknet19 config and weights and creates...

goodwillyoga

Getting error TypeError: buffer is too small for requested array with Memory Warning, while converting into H5

1

Hello ALL, I tried to convert [this](https://github.com/azmathmoosa/azFace) weights and cfg files. And Even I tried to use new cfg files as mentioned in https://github.com/pjreddie/darknet/tree/master/cfg . But no success and still...

vasanthhr

I'm getting the error when using the combination of package_dataset.py [https://github.com/alecGraves/DATA/blob/master/package_dataset.py](url) by alec to create npz file for images and bounding boxes and running retrain_yolo.py The error is happening with...

goodwillyoga

when trying'./yad2k.py yolo.cfg yolo.weights model_data/yolo.h5', has problem

2

/root/anaconda3/envs/yad2k/lib/python3.6/site-packages/h5py/__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`. from ._conv import register_converters as...

techDeng

Hi, I am trying to load tiny yolo v2 voc weights to yolo network in tensorflow. It loads successfully, however it does not detects any object. Here is the link...

Ajaz-Ahmad

problem about NMS algroithm

1

I think we shpuld do NMS on the boxes for each class. But using tf.image.non_max_suppression means you treat all classes equally. It may be bad.

xiaohu2015

TypeError: buffer is too small for requested array

4

thanks,I got error, How can I do? File "E:/yad2k/yad2k.py", line 156, in _main buffer=weights_file.read(weights_size * 4)) # weights_size = 28311552 TypeError: buffer is too small for requested array TypeError: buffer...

gbusr

Functional darknet model not detecting any boxes after conversion

1

Hello! I trained my own custom model on 1136 images (so a very small dataset) to detect pedestrian crossing signals, and it has been functional on our test images in...

annieke

ValueError: Dimension 0 in both shapes must be equal, but are 1 and 70. Shapes are [1,1,1024,105] and [70,1024,1,1]. for 'Assign_110' (op: 'Assign') with input shapes: [1,1,1024,105], [70,1024,1,1]. File "draw_ademawe.py",...

ahmdkamal

Where can I download the converted H5 file?

8

Where can I download the converted H5 file?

tianshangwuyun