Open xinsuinizhuan opened 4 years ago
@xinsuinizhuan Cloud you share the source code of xYOLO?
I've created xyolo.cfg like this, [net]
batch=64 subdivisions=8 width=256 height=256 channels=3 momentum=0.9 decay=0.0005 angle=0 saturation = 1.5 exposure = 1.5 hue=.1
learning_rate=0.001 burn_in=1000 max_batches = 40000 policy=steps steps=128000,216000 scales=.1,.1
[convolutional] batch_normalize=1 filters=2 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] bin_output=1 batch_normalize=1 filters=4 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] bin_output=1 batch_normalize=1 filters=8 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=2
[convolutional] bin_output=1 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] bin_output=1 batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky
[maxpool] size=2 stride=1
[convolutional] xnor=1 bin_output=1 batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky
###########
[convolutional] xnor=1 batch_normalize=1 filters=32 size=1 stride=1 pad=1 activation=leaky
[convolutional] xnor=1 batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky
[convolutional] xnor=1 size=1 stride=1 pad=1 filters=75 activation=leaky
[yolo] mask = 3,4,5 anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319 classes=20 num=6 jitter=.3 ignore_thresh = .7 truth_thresh = 1 random=1
[route] layers = -4
[convolutional] batch_normalize=1 filters=16 size=1 stride=1 pad=1 activation=leaky
[upsample] stride=2
[route] layers = -1, 8
[convolutional] batch_normalize=1 filters=32 size=3 stride=1 pad=1 activation=leaky
[convolutional] size=1 stride=1 pad=1 filters=75 activation=linear
[yolo] mask = 0,1,2 anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319 classes=20 num=6 jitter=.3 ignore_thresh = .7 truth_thresh = 1 random=1 And when I lauched my trainning, I've got some segmentation erros in function binarize_weights (). Could you please give me some help?
Hi everyone, This is achieved by trading an acceptable amount of accuracy, making the network approximately 70 times faster than Tiny-YOLO.Greater inference speed-ups were also achieved on a desktop CPU and GPU. Additionally we contribute an annotated Darknet dataset for goal and ball detection.
https://arxiv.org/pdf/1910.03159.pdf