Bienqq
/
car-detection-bayes
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

updates

This commit is contained in:
Glenn Jocher 2019-07-20 01:28:29 +02:00
parent d1abe51876
commit d6edefa8ab
3 changed files with 34 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
models.py
View File

@ -34,6 +34,7 @@ def create_modules(module_defs):
if bn:
modules.add_module('batch_norm_%d' % i, nn.BatchNorm2d(filters))
if module_def['activation'] == 'leaky':
# modules.add_module('leaky_%d' % i, nn.PReLU(num_parameters=filters, init=0.10))
modules.add_module('leaky_%d' % i, nn.LeakyReLU(0.1, inplace=True))
elif module_def['type'] == 'maxpool':

56
train.py
View File

@ -11,44 +11,48 @@ from models import *
from utils.datasets import *
from utils.utils import *
# 320 --epochs 1
# 0.109 0.297 0.15 0.126 7.04 1.666 4.062 0.1845 42.6 3.34 12.61 8.338 0.2705 0.001 -4 0.9 0.0005 320 giou + best_anchor False
# 0.223 0.218 0.138 0.189 9.28 1.153 4.376 0.08263 24.28 3.05 20.93 2.842 0.2759 0.001357 -5.036 0.9158 0.0005722 mAP/F1 - 50/50 weighting
# 0.231 0.215 0.135 0.191 9.51 1.432 3.007 0.06082 24.87 3.477 24.13 2.802 0.3436 0.001127 -5.036 0.9232 0.0005874
# 0.246 0.194 0.128 0.192 8.12 1.101 3.954 0.0817 22.83 3.967 19.83 1.779 0.3352 0.000895 -5.036 0.9238 0.0007973
# 0.242 0.296 0.196 0.231 5.67 0.8541 4.286 0.1539 21.61 1.957 22.9 2.894 0.3689 0.001844 -4 0.913 0.000467 # ha
# 0.187 0.237 0.144 0.186 14.6 1.607 4.202 0.09439 39.27 3.726 31.26 2.634 0.273 0.001542 -5.036 0.8364 0.0008393
# 320 --epochs 2
# 0.242 0.296 0.196 0.231 5.67 0.8541 4.286 0.1539 21.61 1.957 22.9 2.894 0.3689 0.001844 -4 0.913 0.000467 # ha 0.417 mAP @ epoch 100
# 0.298 0.244 0.167 0.247 4.99 0.8896 4.067 0.1694 21.41 2.033 25.61 1.783 0.4115 0.00128 -4 0.950 0.000377 # hb
# 0.268 0.268 0.178 0.240 4.36 1.104 5.596 0.2087 14.47 2.599 16.27 2.406 0.4114 0.001585 -4 0.950 0.000524 # hc
# 0.161 0.327 0.190 0.193 7.82 1.153 4.062 0.1845 24.28 3.05 20.93 2.842 0.2759 0.001357 -4 0.916 0.000572 # hd 320 --epochs 2
# Training hyperparameters a
hyp = {'giou': 0.8541, # giou loss gain
'xy': 4.062, # xy loss gain
'wh': 0.1845, # wh loss gain
'cls': 21.61, # cls loss gain
'cls_pw': 1.957, # cls BCELoss positive_weight
'obj': 22.9, # obj loss gain
'obj_pw': 2.894, # obj BCELoss positive_weight
'iou_t': 0.3689, # iou target-anchor training threshold
'lr0': 0.001844, # initial learning rate
'lrf': -4., # final learning rate = lr0 * (10 ** lrf)
'momentum': 0.913, # SGD momentum
'weight_decay': 0.000467} # optimizer weight decay
# 0.161 0.327 0.190 0.193 7.82 1.153 4.062 0.1845 24.28 3.05 20.93 2.842 0.2759 0.001357 -4 0.916 0.000572 # hd 0.438 mAP @ epoch 100
# Training hyperparameters d
# hyp = {'giou': 1.153, # giou loss gain
hyp = {'giou': 1.153, # giou loss gain
'xy': 4.062, # xy loss gain
'wh': 0.1845, # wh loss gain
'cls': 24.28, # cls loss gain
'cls_pw': 3.05, # cls BCELoss positive_weight
'obj': 20.93, # obj loss gain
'obj_pw': 2.842, # obj BCELoss positive_weight
'iou_t': 0.2759, # iou target-anchor training threshold
'lr0': 0.001357, # initial learning rate
'lrf': -4., # final learning rate = lr0 * (10 ** lrf)
'momentum': 0.916, # SGD momentum
'weight_decay': 0.000572} # optimizer weight decay
# # Training hyperparameters e
# hyp = {'giou': 1.607, # giou loss gain
# 'xy': 4.062, # xy loss gain
# 'wh': 0.1845, # wh loss gain
# 'cls': 24.28, # cls loss gain
# 'cls_pw': 3.05, # cls BCELoss positive_weight
# 'obj': 20.93, # obj loss gain
# 'obj_pw': 2.842, # obj BCELoss positive_weight
# 'iou_t': 0.2759, # iou target-anchor training threshold
# 'lr0': 0.001357, # initial learning rate
# 'cls': 39.27, # cls loss gain
# 'cls_pw': 3.726, # cls BCELoss positive_weight
# 'obj': 31.26, # obj loss gain
# 'obj_pw': 2.634, # obj BCELoss positive_weight
# 'iou_t': 0.273, # iou target-anchor training threshold
# 'lr0': 0.001542, # initial learning rate
# 'lrf': -4., # final learning rate = lr0 * (10 ** lrf)
# 'momentum': 0.916, # SGD momentum
# 'weight_decay': 0.000572} # optimizer weight decay
# 'momentum': 0.8364, # SGD momentum
# 'weight_decay': 0.0008393} # optimizer weight decay
def train(cfg,

5
utils/utils.py
View File

@ -534,11 +534,12 @@ def coco_only_people(path='../coco/labels/val2014/'):
print(labels.shape[0], file)
def select_best_evolve(path='../../Downloads/evolve*.txt'): # from utils.utils import *; select_best_evolve()
def select_best_evolve(path='evolve*.txt'): # from utils.utils import *; select_best_evolve()
# Find best evolved mutation
for file in sorted(glob.glob(path)):
x = np.loadtxt(file, dtype=np.float32)
print(file, x[x[:, 2].argmax()])
fitness = x[:, 2] * 0.5 + x[:, 3] * 0.5 # weighted mAP and F1 combination
print(file, x[fitness.argmax()])
def kmeans_targets(path='./data/coco_64img.txt'): # from utils.utils import *; kmeans_targets()