darkflow
darkflow copied to clipboard
thtrieu
AssertionError: labels.txt and cfg/yolov2.cfg indicate inconsistent class numbers
so i try to use the code from https://github.com/markjay4k/YOLO-series/blob/master/part2%20-%20Processing%20Images%20with%20YOLO%20and%20openCV.ipynb and i try to change yolo.cfg to yolov2.cfg and then this error appears can someone please help me
I have the same issue. Did you create weights file using darknet? I did it.
@keides2 hello, I create weights file using darknet,then AssertionError: labels.txt and cfg/yolov2.cfg indicate inconsistent class numbers,can i solve this question?
@ss199302 Hi, Does the number of classes of objects described in labes.txt match with the number of classes described on line 244 of cfg / yolov2.cfg?
if you are using dark flow then, copy this:-
person bicycle car motorbike aeroplane bus train truck boat traffic light fire hydrant stop sign parking meter bench bird cat dog horse sheep cow elephant bear zebra giraffe backpack umbrella handbag tie suitcase frisbee skis snowboard sports ball kite baseball bat baseball glove skateboard surfboard tennis racket bottle wine glass cup fork knife spoon bowl banana apple sandwich orange broccoli carrot hot dog pizza donut cake chair sofa pottedplant bed diningtable toilet tvmonitor laptop mouse remote keyboard cell phone microwave oven toaster sink refrigerator book clock vase scissors teddy bear hair drier toothbrush
-- till toothbrush. copied from coco.names from cfg folder and it worked for me.
if you are using dark flow then,
copy this:- person bicycle car motorbike aeroplane bus train truck boat traffic light fire hydrant stop sign parking meter bench bird cat dog horse sheep cow elephant bear zebra giraffe backpack umbrella handbag tie suitcase frisbee skis snowboard sports ball kite baseball bat baseball glove skateboard surfboard tennis racket bottle wine glass cup fork knife spoon bowl banana apple sandwich orange broccoli carrot hot dog pizza donut cake chair sofa pottedplant bed diningtable toilet tvmonitor laptop mouse remote keyboard cell phone microwave oven toaster sink refrigerator book clock vase scissors teddy bear hair drier toothbrush
-- till toothbrush. copied from coco.names from cfg folder and it worked for me.
THANKS MAN!! This works for me. I spent like 2 hours to find this.
I used my own dataset to train model in darkflow which contains 7 classes and i have mentioned those classes in labels.txt as well. I've changed the no. of filters to 60 and classes to 7 in .cfg file as well but even though I'm having an error. Which reads:
Parsing ./cfg/yolo.cfg
Parsing cfg/yolo-7c.cfg
Loading bin/yolo.weights ...
Successfully identified 203934260 bytes
Finished in 0.006638526916503906s
Traceback (most recent call last):
File "/home/mirait/anaconda3/envs/test/bin/flow", line 6, in
my cfg file is:
[net] batch=64 subdivisions=8 width=416 height=416 channels=3 momentum=0.9 decay=0.0005 angle=0 saturation = 1.5 exposure = 1.5 hue=.1
learning_rate=0.001 max_batches = 40100 policy=steps steps=-1,100,20000,30000 scales=.1,10,.1,.1
[convolutional] batch_normalize=1 filters=16 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=1
[convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky
###########
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] size=1 stride=1 pad=1 filters=60 activation=linear
[region] anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52 bias_match=1 classes=7 coords=4 num=5 softmax=1 jitter=.2 rescore=1
object_scale=5 noobject_scale=1 class_scale=1 coord_scale=1
absolute=1 thresh = .5 random=1
my labels.txt file contains: 1.bear 2.boar 3.cat 4.crow 5.deer 6.dog 7.monkey
but i'm getting error which reads:
AssertionError: labels.txt and cfg/tiny-yolo-voc-7c.cfg indicate inconsistent class numbers
my cfg file is:
[net] batch=64 subdivisions=8 width=416 height=416 channels=3 momentum=0.9 decay=0.0005 angle=0 saturation = 1.5 exposure = 1.5 hue=.1
learning_rate=0.001 max_batches = 40100 policy=steps steps=-1,100,20000,30000 scales=.1,10,.1,.1
[convolutional] batch_normalize=1 filters=16 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=1
[convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky
###########
[convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky
[convolutional] size=1 stride=1 pad=1 filters=60 activation=linear
[region] anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52 bias_match=1 classes=7 coords=4 num=5 softmax=1 jitter=.2 rescore=1
object_scale=5 noobject_scale=1 class_scale=1 coord_scale=1
absolute=1 thresh = .5 random=1
my labels.txt file contains: 1.bear 2.boar 3.cat 4.crow 5.deer 6.dog 7.monkey
but i'm getting error which reads:
AssertionError: labels.txt and cfg/tiny-yolo-voc-7c.cfg indicate inconsistent class numbers
Hi brother, I solved that.You can solve that with change coco.names .Because it used coco.names for get labels sometimes.Just open coc.names ,delete all and put your labels like label.txt structures
I solved that.You can solve that with change coco.names .Because it used coco.names for get labels sometimes.Just open coc.names ,delete all and put your labels like label.txt structures
This works for me. Thanks
