804 lines
9.1 KiB
INI
804 lines
9.1 KiB
INI
# Generated by Glenn Jocher (glenn.jocher@ultralytics.com) for https://github.com/ultralytics/yolov3
|
|
# def kmean_anchors(path='../coco/train2017.txt', n=12, img_size=(320, 640)): # from utils.utils import *; kmean_anchors()
|
|
# Evolving anchors: 100%|██████████| 1000/1000 [41:15<00:00, 2.48s/it]
|
|
# 0.20 iou_thr: 0.992 best possible recall, 4.25 anchors > thr
|
|
# kmeans anchors (n=12, img_size=(320, 640), IoU=0.005/0.184/0.634-min/mean/best): 6,9, 15,16, 17,35, 37,26, 36,67, 63,42, 57,100, 121,81, 112,169, 241,158, 195,310, 426,359
|
|
|
|
[net]
|
|
# Testing
|
|
# batch=1
|
|
# subdivisions=1
|
|
# Training
|
|
batch=64
|
|
subdivisions=16
|
|
width=608
|
|
height=608
|
|
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
|
|
|
|
# SPP --------------------------------------------------------------------------
|
|
[maxpool]
|
|
stride=1
|
|
size=5
|
|
|
|
[route]
|
|
layers=-2
|
|
|
|
[maxpool]
|
|
stride=1
|
|
size=9
|
|
|
|
[route]
|
|
layers=-4
|
|
|
|
[maxpool]
|
|
stride=1
|
|
size=13
|
|
|
|
[route]
|
|
layers=-1,-3,-5,-6
|
|
# SPP --------------------------------------------------------------------------
|
|
|
|
[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=258
|
|
activation=linear
|
|
|
|
# YOLO -------------------------------------------------------------------------
|
|
|
|
[route]
|
|
layers = -3
|
|
|
|
[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=258
|
|
activation=linear
|
|
|
|
# YOLO -------------------------------------------------------------------------
|
|
|
|
[route]
|
|
layers = -3
|
|
|
|
[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=258
|
|
activation=linear
|
|
|
|
[yolo]
|
|
from=88,99,110
|
|
mask = 8,9,10,11
|
|
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=9
|
|
|
|
[yolo]
|
|
from=88,99,110
|
|
mask = 4,5,6,7
|
|
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=9
|
|
|
|
[yolo]
|
|
from=88,99,110
|
|
mask = 0,1,2,3
|
|
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
|
classes=80
|
|
num=9 |