mirror of
https://github.com/huggingface/candle.git
synced 2025-06-15 10:26:33 +00:00
a1812f934f
* Add a couple functions required for yolo. * Add the yolo-v3 example. * Add minimum and maximum. * Use the newly introduced maximum. * Cuda support for min/max + add some testing. * Allow for more tests to work with accelerate. * Fix a typo.
791 lines
8.2 KiB
INI
791 lines
8.2 KiB
INI
[net]
|
|
# Testing
|
|
batch=1
|
|
subdivisions=1
|
|
# Training
|
|
# batch=64
|
|
# subdivisions=16
|
|
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
|
|
burn_in=1000
|
|
max_batches = 500200
|
|
policy=steps
|
|
steps=400000,450000
|
|
scales=.1,.1
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=32
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=32
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=64
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
# Downsample
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=2
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=1024
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[shortcut]
|
|
from=-3
|
|
activation=linear
|
|
|
|
######################
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=1024
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=512
|
|
size=1
|
|
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=255
|
|
activation=linear
|
|
|
|
|
|
[yolo]
|
|
mask = 6,7,8
|
|
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=9
|
|
jitter=.3
|
|
ignore_thresh = .5
|
|
truth_thresh = 1
|
|
random=1
|
|
|
|
|
|
[route]
|
|
layers = -4
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1, 61
|
|
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=256
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=512
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=255
|
|
activation=linear
|
|
|
|
|
|
[yolo]
|
|
mask = 3,4,5
|
|
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=9
|
|
jitter=.3
|
|
ignore_thresh = .5
|
|
truth_thresh = 1
|
|
random=1
|
|
|
|
|
|
|
|
[route]
|
|
layers = -4
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[upsample]
|
|
stride=2
|
|
|
|
[route]
|
|
layers = -1, 36
|
|
|
|
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
filters=128
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
batch_normalize=1
|
|
size=3
|
|
stride=1
|
|
pad=1
|
|
filters=256
|
|
activation=leaky
|
|
|
|
[convolutional]
|
|
size=1
|
|
stride=1
|
|
pad=1
|
|
filters=255
|
|
activation=linear
|
|
|
|
|
|
[yolo]
|
|
mask = 0,1,2
|
|
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=9
|
|
jitter=.3
|
|
ignore_thresh = .5
|
|
truth_thresh = 1
|
|
random=1
|
|
|