Comments (18)
@djebm2, I have not modified the source code to run it. By the way I have a newer version that is now training with loss errors below 1.
[net]
batch=128
subdivisions=2
height=227
width=227
channels=3
momentum=0.9
decay=0.0005
learning_rate=0.001
policy=steps
steps=20,40,60,80,20000,30000
scales=5,5,2,2,.1,.1
max_batches=40000
[crop]
crop_width=227
crop_height=227
flip=0
angle=0
saturation = 1.5
exposure = 1.5
# SqueezeNet: conv1
[convolutional]
filters=64
size=3
stride=2
activation=relu
# SqueezeNet: pool1
[maxpool]
size=3
stride=2
# SqueezeNet: fire2/squeeze1x1
[convolutional]
filters=16
size=1
activation=relu
# SqueezeNet: fire2/expand1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire2/shortcut
[route]
layers=-2
# SqueezeNet: fire2/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire2/route
[route]
layers=-3,-1
# SqueezeNet: fire3/squeeze1x1
[convolutional]
filters=16
size=1
activation=relu
# SqueezeNet:fire3/expand1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire3/shortcut
[route]
layers=-2
# SqueezeNet: fire3/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire3/route
[route]
layers=-3,-1
# SqueezeNet: pool3
[maxpool]
size=3
stride=2
# SqueezeNet: fire4/squeeze1x1
[convolutional]
filters=32
size=1
activation=relu
# SqueezeNet: fire4/expand1x1
[convolutional]
filters=128
size=1
activation=relu
# SqueezeNet: fire4/shortcut
[route]
layers=-2
# SqueezeNet: fire4/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire4/route
[route]
layers=-3,-1
# SqueezeNet: fire5/squeeze1x1
[convolutional]
filters=32
size=1
activation=relu
# SqueezeNet: fire5/expand1x1
[convolutional]
filters=128
size=1
activation=relu
# SqueezeNet: fire5/shortcut
[route]
layers=-2
# SqueezeNet: fire5/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire5/route
[route]
layers=-3,-1
# SqueezeNet: pool5
[maxpool]
size=3
stride=2
# SqueezeNet: fire6/squeeze1x1
[convolutional]
filters=48
size=1
activation=relu
# SqueezeNet: fire6/expand1x1
[convolutional]
filters=192
size=1
activation=relu
# SqueezeNet: fire6/shortcut
[route]
layers=-2
# SqueezeNet: fire6/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire6/route
[route]
layers=-3,-1
# SqueezeNet: fire7/squeeze1x1
[convolutional]
filters=48
size=1
activation=relu
# SqueezeNet: fire7/expand1x1
[convolutional]
filters=192
size=1
activation=relu
# SqueezeNet: fire7/shortcut
[route]
layers=-2
# SqueezeNet: fire7/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire7/route
[route]
layers=-3,-1
# SqueezeNet: fire8/squeeze1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire8/expand1x1
[convolutional]
filters=256
size=1
activation=relu
# SqueezeNet: fire8/shortcut
[route]
layers=-2
# SqueezeNet: fire8/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire8/route
[route]
layers=-3,-1
# SqueezeNet: fire9/squeeze1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire9/expand1x1
[convolutional]
filters=256
size=1
activation=relu
# SqueezeNet: fire9/shortcut
[route]
layers=-2
# SqueezeNet: fire9/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire9/route
[route]
layers=-3,-1
# SqueezeNet: drop9
[dropout]
probability=.5
# SqueezeNet: conv10
[convolutional]
filters=1000
size=1
activation=relu
# SqueezeNet: pool10
[avgpool]
# YoLo: output = (5 * 2 + CLASSES) * SIDE^2
[connected]
output=539
activation=linear
# YoLo
[detection]
classes=1
coords=4
rescore=1
side=7
num=2
softmax=0
sqrt=1
jitter=.2
object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5
from squeezenet.
Great idea! I'm definitely interested in this. Perhaps Mr Darknet (@pjreddie) may also care to weigh in.
The Darknet google group might also be a good place to ask this question: https://groups.google.com/forum/#!forum/darknet
I'm not that experienced with Darknet yet. Do we know if it can handle DAG-shaped CNNs, or only linked lists? I guess this might be the point of the "route" layer, but I haven't looked at darknet/src/route_layer.c
in detail.
from squeezenet.
We may could invite the R-FCN author too, what do you think @daijifeng001?
from squeezenet.
@forresti I think Darknet implements a DAG style except there is no bi-directional sense of nodes connections. In other works, .cfg processing is procedural, but shortcut and route layers allow us to connect previous nodes/connections to the current one.
from squeezenet.
I found some errors on my previous Darknet/squeezenet.cfg... still got stuck at 5~6 loss error.
batch=128
subdivisions=2
height=227
width=227
channels=3
momentum=0.9
decay=0.0005
learning_rate=0.001
policy=steps
steps=20,40,60,80,20000,30000
scales=5,5,2,2,.1,.1
max_batches=40000
[crop]
crop_width=227
crop_height=227
flip=0
angle=0
saturation = 1.5
exposure = 1.5
# SqueezeNet: conv1
[convolutional]
filters=64
size=3
stride=2
activation=relu
# SqueezeNet: pool1
[maxpool]
size=3
stride=2
# SqueezeNet: fire2/squeeze1x1
[convolutional]
filters=16
size=1
activation=relu
# SqueezeNet: fire2/expand1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire2/shortcut
[shortcut]
from=-2
# SqueezeNet: fire2/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire2/route
[route]
layers=-3,-1
# SqueezeNet: fire3/squeeze1x1
[convolutional]
filters=16
size=1
activation=relu
# SqueezeNet:fire3/expand1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire3/shortcut
[shortcut]
from=-2
# SqueezeNet: fire3/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire3/route
[route]
layers=-3,-1
# SqueezeNet: pool3
[maxpool]
size=3
stride=2
# SqueezeNet: fire4/squeeze1x1
[convolutional]
filters=32
size=1
activation=relu
# SqueezeNet: fire4/expand1x1
[convolutional]
filters=128
size=1
activation=relu
# SqueezeNet: fire4/shortcut
[shortcut]
from=-2
# SqueezeNet: fire4/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire4/route
[route]
layers=-3,-1
# SqueezeNet: fire5/squeeze1x1
[convolutional]
filters=32
size=1
activation=relu
# SqueezeNet: fire5/expand1x1
[convolutional]
filters=128
size=1
activation=relu
# SqueezeNet: fire5/shortcut
[shortcut]
from=-2
# SqueezeNet: fire5/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire5/route
[route]
layers=-3,-1
# SqueezeNet: pool5
[maxpool]
size=3
stride=2
# SqueezeNet: fire6/squeeze1x1
[convolutional]
filters=48
size=1
activation=relu
# SqueezeNet: fire6/expand1x1
[convolutional]
filters=192
size=1
activation=relu
# SqueezeNet: fire6/shortcut
[shortcut]
from=-2
# SqueezeNet: fire6/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire6/route
[route]
layers=-3,-1
# SqueezeNet: fire7/squeeze1x1
[convolutional]
filters=48
size=1
activation=relu
# SqueezeNet: fire7/expand1x1
[convolutional]
filters=192
size=1
activation=relu
# SqueezeNet: fire7/shortcut
[shortcut]
from=-2
# SqueezeNet: fire7/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire7/route
[route]
layers=-3,-1
# SqueezeNet: fire8/squeeze1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire8/expand1x1
[convolutional]
filters=256
size=1
activation=relu
# SqueezeNet: fire8/shortcut
[shortcut]
from=-2
# SqueezeNet: fire8/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire8/route
[route]
layers=-3,-1
# SqueezeNet: fire9/squeeze1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire9/expand1x1
[convolutional]
filters=256
size=1
activation=relu
# SqueezeNet: fire9/shortcut
[shortcut]
from=-2
# SqueezeNet: fire9/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire9/route
[route]
layers=-3,-1
# SqueezeNet: drop9
[dropout]
probability=.5
# SqueezeNet: conv10
[convolutional]
filters=1000
size=1
activation=relu
# SqueezeNet: pool10
[avgpool]
# YoLo: output = (5 * 2 + CLASSES) * SIDE^2
[connected]
output=539
activation=linear
# YoLo
[detection]
classes=1
coords=4
rescore=1
side=7
num=2
softmax=0
sqrt=1
jitter=.2
object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5```
from squeezenet.
Thank you for sharing. However, your model triggers a seg fault when running the yolo training. Have you changed the source code as well ? thx.
from squeezenet.
Cfg file looks good, I think the first layer is 7x7 though right? Have you
pre trained in image net? I'll try when I get home
On Sep 7, 2016 7:23 PM, "Luiz Vitor Martinez Cardoso" <
[email protected]> wrote:
@djebm2 https://github.com/djebm2, I have not modified the source code
to run it. By the way I have a newer version that is now training with loss
errors below 1.[net]
batch=128
subdivisions=2
height=227
width=227
channels=3
momentum=0.9
decay=0.0005learning_rate=0.001
policy=steps
steps=20,40,60,80,20000,30000
scales=5,5,2,2,.1,.1
max_batches=40000[crop]
crop_width=227
crop_height=227
flip=0
angle=0
saturation = 1.5
exposure = 1.5SqueezeNet: conv1
[convolutional]
filters=64
size=3
stride=2
activation=reluSqueezeNet: pool1
[maxpool]
size=3
stride=2SqueezeNet: fire2/squeeze1x1
[convolutional]
filters=16
size=1
activation=reluSqueezeNet: fire2/expand1x1
[convolutional]
filters=64
size=1
activation=reluSqueezeNet: fire2/shortcut
[route]
layers=-2SqueezeNet: fire2/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=reluSqueezeNet: fire2/route
[route]
layers=-3,-1SqueezeNet: fire3/squeeze1x1
[convolutional]
filters=16
size=1
activation=reluSqueezeNet:fire3/expand1x1
[convolutional]
filters=64
size=1
activation=reluSqueezeNet: fire3/shortcut
[route]
layers=-2SqueezeNet: fire3/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=reluSqueezeNet: fire3/route
[route]
layers=-3,-1SqueezeNet: pool3
[maxpool]
size=3
stride=2SqueezeNet: fire4/squeeze1x1
[convolutional]
filters=32
size=1
activation=reluSqueezeNet: fire4/expand1x1
[convolutional]
filters=128
size=1
activation=reluSqueezeNet: fire4/shortcut
[route]
layers=-2SqueezeNet: fire4/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=reluSqueezeNet: fire4/route
[route]
layers=-3,-1SqueezeNet: fire5/squeeze1x1
[convolutional]
filters=32
size=1
activation=reluSqueezeNet: fire5/expand1x1
[convolutional]
filters=128
size=1
activation=reluSqueezeNet: fire5/shortcut
[route]
layers=-2SqueezeNet: fire5/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=reluSqueezeNet: fire5/route
[route]
layers=-3,-1SqueezeNet: pool5
[maxpool]
size=3
stride=2SqueezeNet: fire6/squeeze1x1
[convolutional]
filters=48
size=1
activation=reluSqueezeNet: fire6/expand1x1
[convolutional]
filters=192
size=1
activation=reluSqueezeNet: fire6/shortcut
[route]
layers=-2SqueezeNet: fire6/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=reluSqueezeNet: fire6/route
[route]
layers=-3,-1SqueezeNet: fire7/squeeze1x1
[convolutional]
filters=48
size=1
activation=reluSqueezeNet: fire7/expand1x1
[convolutional]
filters=192
size=1
activation=reluSqueezeNet: fire7/shortcut
[route]
layers=-2SqueezeNet: fire7/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=reluSqueezeNet: fire7/route
[route]
layers=-3,-1SqueezeNet: fire8/squeeze1x1
[convolutional]
filters=64
size=1
activation=reluSqueezeNet: fire8/expand1x1
[convolutional]
filters=256
size=1
activation=reluSqueezeNet: fire8/shortcut
[route]
layers=-2SqueezeNet: fire8/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=reluSqueezeNet: fire8/route
[route]
layers=-3,-1SqueezeNet: fire9/squeeze1x1
[convolutional]
filters=64
size=1
activation=reluSqueezeNet: fire9/expand1x1
[convolutional]
filters=256
size=1
activation=reluSqueezeNet: fire9/shortcut
[route]
layers=-2SqueezeNet: fire9/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=reluSqueezeNet: fire9/route
[route]
layers=-3,-1SqueezeNet: drop9
[dropout]
probability=.5SqueezeNet: conv10
[convolutional]
filters=1000
size=1
activation=reluSqueezeNet: pool10
[avgpool]
YoLo: output = (5 * 2 + CLASSES) * SIDE^2
[connected]
output=539
activation=linearYoLo
[detection]
classes=1
coords=4
rescore=1
side=7
num=2
softmax=0
sqrt=1
jitter=.2object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5```—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#15 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AAScHJOX2a7ZQVMLdWoIu42Oo4ZhHo4uks5qn3G5gaJpZM4JD4oZ
.
from squeezenet.
@pjreddie it is good to hear from you buddy!
Please check my latest versions of SqueezeNet for Darknet with route layers and batchnormalization. Please the check following variants:
[net]
batch=64
subdivisions=2
height=227
width=227
channels=3
momentum=0.9
decay=0.0005
learning_rate=0.001
policy=poly
power=1
max_batches=20000
[crop]
crop_width=227
crop_height=227
flip=0
angle=0
saturation=1.5
exposure=1.5
# SqueezeNet: conv1
[convolutional]
filters=64
size=3
stride=2
activation=relu
# SqueezeNet: pool1
[maxpool]
size=3
stride=2
[batchnorm]
# SqueezeNet: fire2/squeeze1x1
[convolutional]
filters=16
size=1
activation=relu
# SqueezeNet: fire2/expand1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire2/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire2/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire2/route
[route]
layers=-3,-1
[batchnorm]
# SqueezeNet: fire3/squeeze1x1
[convolutional]
filters=16
size=1
activation=relu
# SqueezeNet:fire3/expand1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire3/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire3/expand3x3
[convolutional]
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire3/route
[route]
layers=-3,-1
[batchnorm]
# SqueezeNet: pool3
[maxpool]
size=3
stride=2
[batchnorm]
# SqueezeNet: fire4/squeeze1x1
[convolutional]
filters=32
size=1
activation=relu
# SqueezeNet: fire4/expand1x1
[convolutional]
filters=128
size=1
activation=relu
# SqueezeNet: fire4/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire4/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire4/route
[route]
layers=-3,-1
[batchnorm]
# SqueezeNet: fire5/squeeze1x1
[convolutional]
filters=32
size=1
activation=relu
# SqueezeNet: fire5/expand1x1
[convolutional]
filters=128
size=1
activation=relu
# SqueezeNet: fire5/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire5/expand3x3
[convolutional]
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire5/route
[route]
layers=-3,-1
# SqueezeNet: pool5
[maxpool]
size=3
stride=2
[batchnorm]
# SqueezeNet: fire6/squeeze1x1
[convolutional]
filters=48
size=1
activation=relu
# SqueezeNet: fire6/expand1x1
[convolutional]
filters=192
size=1
activation=relu
# SqueezeNet: fire6/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire6/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire6/route
[route]
layers=-3,-1
[batchnorm]
# SqueezeNet: fire7/squeeze1x1
[convolutional]
filters=48
size=1
activation=relu
# SqueezeNet: fire7/expand1x1
[convolutional]
filters=192
size=1
activation=relu
# SqueezeNet: fire7/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire7/expand3x3
[convolutional]
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire7/route
[route]
layers=-3,-1
[batchnorm]
# SqueezeNet: fire8/squeeze1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire8/expand1x1
[convolutional]
filters=256
size=1
activation=relu
# SqueezeNet: fire8/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire8/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire8/route
[route]
layers=-3,-1
[batchnorm]
# SqueezeNet: fire9/squeeze1x1
[convolutional]
filters=64
size=1
activation=relu
# SqueezeNet: fire9/expand1x1
[convolutional]
filters=256
size=1
activation=relu
# SqueezeNet: fire9/shortcut
[shortcut]
from=-2
activation=leaky
# SqueezeNet: fire9/expand3x3
[convolutional]
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire9/route
[route]
layers=-3,-1
# SqueezeNet: drop9
[dropout]
probability=.5
# SqueezeNet: conv10
[convolutional]
filters=1000
size=1
activation=relu
[batchnorm]
# SqueezeNet: pool10
[avgpool]
# YoLo: output = (5 * 2 + CLASSES) * SIDE^2
[connected]
output=539
activation=linear
# YoLo
[detection]
classes=1
coords=4
rescore=1
side=7
num=2
softmax=0
sqrt=1
jitter=.2
object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5
OR
[net]
batch=64
subdivisions=2
height=227
width=227
channels=3
momentum=0.9
decay=0.0005
learning_rate=0.04
policy=poly
power=1
max_batches=200000
[crop]
crop_width=227
crop_height=227
flip=0
angle=0
saturation=1.5
exposure=1.5
# SqueezeNet: conv1
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
activation=relu
# SqueezeNet: pool1
[maxpool]
size=3
stride=2
# SqueezeNet: fire2/squeeze1x1
[convolutional]
batch_normalize=1
filters=16
size=1
activation=relu
# SqueezeNet: fire2/expand1x1
[convolutional]
batch_normalize=1
filters=64
size=1
activation=relu
# SqueezeNet: fire2/route
[route]
layers=-2
# SqueezeNet: fire2/expand3x3
[convolutional]
batch_normalize=1
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire2/route
[route]
layers=-3,-1
# SqueezeNet: fire3/squeeze1x1
[convolutional]
batch_normalize=1
filters=16
size=1
activation=relu
# SqueezeNet:fire3/expand1x1
[convolutional]
batch_normalize=1
filters=64
size=1
activation=relu
# SqueezeNet: fire3/route
[route]
layers=-2
# SqueezeNet: fire3/expand3x3
[convolutional]
batch_normalize=1
filters=64
size=3
pad=1
activation=relu
# SqueezeNet: fire3/route
[route]
layers=-3,-1
# SqueezeNet: pool3
[maxpool]
size=3
stride=2
# SqueezeNet: fire4/squeeze1x1
[convolutional]
batch_normalize=1
filters=32
size=1
activation=relu
# SqueezeNet: fire4/expand1x1
[convolutional]
batch_normalize=1
filters=128
size=1
activation=relu
# SqueezeNet: fire4/route
[route]
layers=-2
# SqueezeNet: fire4/expand3x3
[convolutional]
batch_normalize=1
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire4/route
[route]
layers=-3,-1
# SqueezeNet: fire5/squeeze1x1
[convolutional]
batch_normalize=1
filters=32
size=1
activation=relu
# SqueezeNet: fire5/expand1x1
[convolutional]
batch_normalize=1
filters=128
size=1
activation=relu
# SqueezeNet: fire5/route
[route]
layers=-2
# SqueezeNet: fire5/expand3x3
[convolutional]
batch_normalize=1
filters=128
size=3
pad=1
activation=relu
# SqueezeNet: fire5/route
[route]
layers=-3,-1
# SqueezeNet: pool5
[maxpool]
size=3
stride=2
# SqueezeNet: fire6/squeeze1x1
[convolutional]
batch_normalize=1
filters=48
size=1
activation=relu
# SqueezeNet: fire6/expand1x1
[convolutional]
batch_normalize=1
filters=192
size=1
activation=relu
# SqueezeNet: fire6/route
[route]
layers=-2
# SqueezeNet: fire6/expand3x3
[convolutional]
batch_normalize=1
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire6/route
[route]
layers=-3,-1
# SqueezeNet: fire7/squeeze1x1
[convolutional]
batch_normalize=1
filters=48
size=1
activation=relu
# SqueezeNet: fire7/expand1x1
[convolutional]
batch_normalize=1
filters=192
size=1
activation=relu
# SqueezeNet: fire7/route
[route]
layers=-2
# SqueezeNet: fire7/expand3x3
[convolutional]
batch_normalize=1
filters=192
size=3
pad=1
activation=relu
# SqueezeNet: fire7/route
[route]
layers=-3,-1
# SqueezeNet: fire8/squeeze1x1
[convolutional]
batch_normalize=1
filters=64
size=1
activation=relu
# SqueezeNet: fire8/expand1x1
[convolutional]
batch_normalize=1
filters=256
size=1
activation=relu
# SqueezeNet: fire8/route
[route]
layers=-2
# SqueezeNet: fire8/expand3x3
[convolutional]
batch_normalize=1
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire8/route
[route]
layers=-3,-1
# SqueezeNet: fire9/squeeze1x1
[convolutional]
batch_normalize=1
filters=64
size=1
activation=relu
# SqueezeNet: fire9/expand1x1
[convolutional]
batch_normalize=1
filters=256
size=1
activation=relu
# SqueezeNet: fire9/route
[route]
layers=-2
# SqueezeNet: fire9/expand3x3
[convolutional]
batch_normalize=1
filters=256
size=3
pad=1
activation=relu
# SqueezeNet: fire9/route
[route]
layers=-3,-1
# SqueezeNet: drop9
[dropout]
probability=.5
# SqueezeNet: conv10
[convolutional]
batch_normalize=1
filters=1000
size=1
activation=relu
# SqueezeNet: pool10
[avgpool]
# YoLo: output = (5 * 2 + CLASSES) * SIDE^2
[connected]
output=1331
activation=linear
# YoLo
[detection]
classes=1
coords=4
rescore=1
side=11
num=2
softmax=0
sqrt=1
jitter=.2
object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5
from squeezenet.
the avgpool layer will be really bad for detection since you throw out all
the spatial information. It's good for classification but you should get
rid of it and the last 1000 filter convolutional layer for detection.
Also, just so you know, squeezenet is good in terms of the number of
parameters but it's still uses lots of floating point operations.
squeezenet uses 2.17 billion operations while the standard darknet config:
https://github.com/pjreddie/darknet/blob/master/cfg/darknet.cfg
only uses .81 billion operations so it'll probably be faster.
On Wed, Sep 7, 2016 at 9:41 PM, Luiz Vitor Martinez Cardoso <
[email protected]> wrote:
@pjreddie https://github.com/pjreddie it is good to hear from you
buddy!Please check my latest porting versions of SqueezeNet for Darknet. I had
to change route/shortcut layers and use batchnormalization... now loss
error is going below 1 on my datasets.https://bitbucket.org/snippets/geeksys/Ap85M
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#15 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AAScHA08ypMUDnzNC8nd7BMX003d6FCcks5qn5H4gaJpZM4JD4oZ
.
from squeezenet.
@pjreddie, yes. What about enabling xnor=1? Is it working?
from squeezenet.
@pjreddie, by removing
# SqueezeNet: conv10
[convolutional]
batch_normalize=1
filters=1000
size=1
activation=relu
# SqueezeNet: pool10
[avgpool]
Something went totally wrong:
/data/dataset/006_headtop_outdoor/images/out00017358.jpg
Detection Avg IOU: 0.008419, Pos Cat: 0.222350, All Cat: 0.222350, Pos Obj: -285.093384, Any Obj: 94.234314, count: 41
Detection Avg IOU: 0.005466, Pos Cat: 8.992064, All Cat: 8.992064, Pos Obj: -694.999390, Any Obj: 146.219254, count: 35
5: 1363320704.000000, 245519200.000000 avg, 0.039999 rate, 1.584814 seconds, 320 images
Any idea?
from squeezenet.
You can also check out the tiny-yolo model, it's based on the darknet
reference network and it's already trained / i know it works.
http://pjreddie.com/darknet/yolo/#tiny
On Wed, Sep 7, 2016 at 10:35 PM, Luiz Vitor Martinez Cardoso <
[email protected]> wrote:
@pjreddie https://github.com/pjreddie, by removing
SqueezeNet: conv10
[convolutional]
batch_normalize=1
filters=1000
size=1
activation=reluSqueezeNet: pool10
[avgpool]
Something goes totally wrong:
/data/dataset/006_headtop_outdoor/images/out00017358.jpg
Detection Avg IOU: 0.008419, Pos Cat: 0.222350, All Cat: 0.222350, Pos Obj: -285.093384, Any Obj: 94.234314, count: 41
Detection Avg IOU: 0.005466, Pos Cat: 8.992064, All Cat: 8.992064, Pos Obj: -694.999390, Any Obj: 146.219254, count: 35
5: 1363320704.000000, 245519200.000000 avg, 0.039999 rate, 1.584814 seconds, 320 images—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
#15 (comment),
or mute the thread
https://github.com/notifications/unsubscribe-auth/AAScHADi-sbWj39O03662Wi98vYxnL0xks5qn561gaJpZM4JD4oZ
.
from squeezenet.
@pjreddie, I got a push notification about your commit and already started training it. Thanks!
from squeezenet.
@pjreddie What are the upgrades from yolo-tiny to tiny-yolo ? Don't you think removing dropout might impact generalization ?
@Grabber Squeezing tiny-yolo might be a good idea, specially with FP16.
from squeezenet.
@Grabber I think squeezeNet has specially been designed for mimicking AlexNet which natively address the problem of classification. Therefore, as @pjreddie said it, average polling isn't a good idea for detection. I only see an FC layer that could overcome this, but I am afraid the number of parameters would explode and thereby compromise the pruning process.
from squeezenet.
Do avgpooling on a cropped area (where the detected object is) might be useful?
from squeezenet.
@tmatas that is a question that @pjreddie can answer with much more property, I really don't know.
from squeezenet.
@pjreddie Dear pjreddie
can you deliver a pretrained Squeezenet model and cfg in darknet so I can comapre the difference between Squeezenet and tiny darknet
from squeezenet.
Related Issues (20)
- Has anyone successfully trained Squeezenet with residual connections?
- model convert HOT 1
- SqueezeNet v1.1 with Residual Connections with Dense→Sparse→Dense (DSD) Training
- Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1. HOT 4
- Image Width Issue HOT 1
- tensorflow- After hundreds of epochs, my total_loss stay around 0.6~0.7, and not decreased HOT 2
- 1.1 deploy.prototxt HOT 1
- SqueezeNet is slower when using GPU than when using CPU? HOT 2
- training from scratch, random seed HOT 1
- why can not get the output of the prob layer? HOT 1
- SqueezeNet training on cifar HOT 3
- The SqueezeNet deploy.caffemodel files have all 0.0 weight and bias data HOT 1
- Fine-tuning SqueezeNet HOT 2
- which label list you used HOT 1
- why not use lr_mult, decay_mult like {1, 1, 2, 0}? HOT 3
- optimization and compression
- Image normalization values HOT 1
- squeezenet v1_1 for facedetector , possible , feasable ? HOT 1
- squeezenet for speech HOT 3
- Some minor mistakes in the paper HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from squeezenet.