YAD2K

YAD2K copied to clipboard

Quick Start: Anchor file is None

5

Thanks for the great work! I firstly tried with the tiny-yolo, which worked fine. Then I wanted to follow the quick start to see how is the normal yolo2 on...

kuonangzhe

Attempting to use uninitialized value FeatureExtractor/MobilenetV2/expanded_conv_3/depthwise/BatchNorm/beta [[{{node _retval_FeatureExtractor/MobilenetV2/expanded_conv_3/depthwise/BatchNorm/beta_0_179}}]]

1

def _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata): """Runs a step based on the given fetches and feeds. Args: handle: a handle for partial_run. None if this is just a...

vamsikrishnahny

how can detect only one or two class with yolo

2

i want to detect car with yolo and i don't want to detect other object please help me to ommit other class from result

mn7142

np_resource = np.dtype([("resource", np.ubyte, 1)]) Loading weights. Weights Header: [ 0 1 0 15501312] Parsing Darknet config. Traceback (most recent call last): File "./yad2k.py", line 270, in _main(parser.parse_args()) File "./yad2k.py",...

futureflsl

I had a 16gb ram machine but 9 gb was almost and my training data size was little more and was consuming lot of memory. Also data set images are...

mukulbhave

ReLu Activation Function

1

  When I use yad2k, Is LeakyRelu converted to one of above picture? or not Thank you

WantBeACodeer

Implement the new YOLO v3

6

Hi, I love the work you did on YOLO v2. It would be great if you can implement the new YOLO v3 paper: https://pjreddie.com/media/files/papers/YOLOv3.pdf Cheers!

yonatann

Generate yolo.h5 file

1

I get a error message when I run yad2k.py "Traceback (most recent call last): File "yad2k.py", line 270, in _main(parser.parse_args()) File "yad2k.py", line 156, in _main buffer=weights_file.read(weights_size * 4)) TypeError:...

kir9-git

I try to generate yolo.h5 and use this command: python yad2k.py yolo.cfg yolo.weights model_data/yolo.h5

4

File "yad2k.py", line 248, in _main raise ValueError('Unsupported section header type: {}'.format(section)) ValueError: Unsupported section header type: shortcut_0

garychian

yolo_loss

1

in yolo_loss function when calculate`no_object_weights = (no_object_scale * (1 - object_detections) *(1 - detectors_mask))` should `no_object_weights = (no_object_scale * (object_detections) *(1 - detectors_mask))` since no_object_weights is only activated when the...

jjjj4444