YAD2K

YAD2K copied to clipboard

in keras_darknet19.py ``` def darknet19(inputs): """Generate Darknet-19 model for Imagenet classification.""" body = darknet_body()(inputs) logits = DarknetConv2D(1000, (1, 1), activation='softmax')(body) return Model(inputs, logits) ``` question : 1、here 1000 = anchor_num...

speeding-motor

Fix "is directory" check in test_yolo.py

1

I'm proposing this change because the existing implementation gave me an error like this: ``` Traceback (most recent call last): File "test_yolo.py", line 194, in _main(parser.parse_args()) File "test_yolo.py", line 119,...

iver56

… has updated naming conventions due to yolov3 release.

benneely

How to predict via converted yolo9000 model

2

I now want to work on https://github.com/philipperemy/yolo-9000 Follow the instruction, I can already 1. convert the yolo2 weight (for detecting 80 classes in coco_classes.txt) to keras weight, load the yolo2...

veya2ztn

InvalidArgumentError (see above for traceback): Input to reshape is a tensor in Yolov2

3

When I ran the prediction method, this line out_scores, out_boxes, out_classes = sess.run([scores, boxes, classes], feed_dict={yolo_model.input: image_data, K.learning_phase(): 0}) gives me the following error : could any one helps me...

Estapraq

How to give training data to retrain_yolo.py?

4

I don't understand how `retrain_yolo.py` expects the training data. How do I feed my images and my annotation files into retrain_yolo ? Should the images and annotation xml files be...

Nirvan101

ValueError: Cannot feed value of shape (1, 416, 416) for Tensor 'input_1:0', which has shape '(?, 416, 416, 3)'

2

when I use command "python test_yolo.py model_data/yolo.h5", always display "cannot feed value of shape(1,416,416) for Tensor ‘ input_1:0’ ,which has shape '(?,416,416,3)'" problem, have others meet this problem? please explain...

cverzq

fixed yad2k for tiny-yolo

1

fixes #144 #148 #136 ... The current yad2k was giving some errors when executed for `tiny-yolov3.weights`. Fixed `yad2k.py`. Appended the existing code, so won't harm the setting :smile:

prakharcode

I ran the following program. > python yad2k.py yolov2-tiny-voc.cfg yolov2-tiny-voc_2000.weights yolov2tiny.h5 > python test_yolo.py yolov2tiny.h5 -a yolov2tiny_anchors.txt -c coco.names The bounding box shifts right or left from the target. There...

eraser3112

How to replace session.run() with keras Model() for predictions?

look4pritam