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

updates

This commit is contained in:
Glenn Jocher 2019-07-15 17:00:04 +02:00
parent 6893f1daf8
commit 96e25462e8
3 changed files with 39 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
detect.py
View File

@ -7,20 +7,19 @@ from utils.datasets import *
from utils.utils import * from utils.utils import *
def detect( def detect(cfg,
cfg, data_cfg,
data_cfg, weights,
weights, images='data/samples', # input folder
images='data/samples', # input folder output='output', # output folder
output='output', # output folder fourcc='mp4v', # video codec
fourcc='mp4v', img_size=416,
img_size=416, conf_thres=0.5,
conf_thres=0.5, nms_thres=0.5,
nms_thres=0.5, save_txt=False,
save_txt=False, save_images=True,
save_images=True, webcam=False):
webcam=False # Initialize
):
device = torch_utils.select_device() device = torch_utils.select_device()
torch.backends.cudnn.benchmark = False # set False for reproducible results torch.backends.cudnn.benchmark = False # set False for reproducible results
if os.path.exists(output): if os.path.exists(output):
@ -74,7 +73,7 @@ def detect(
if det is not None and len(det) > 0: if det is not None and len(det) > 0:
# Rescale boxes from 416 to true image size # Rescale boxes from 416 to true image size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round() # TODO: clamp to image border https://github.com/ultralytics/yolov3/issues/368 det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
# Print results to screen # Print results to screen
print('%gx%g ' % img.shape[2:], end='') # print image size print('%gx%g ' % img.shape[2:], end='') # print image size

33
test.py
View File

@ -8,18 +8,17 @@ from utils.datasets import *
from utils.utils import * from utils.utils import *
def test( def test(cfg,
cfg, data_cfg,
data_cfg, weights=None,
weights=None, batch_size=16,
batch_size=16, img_size=416,
img_size=416, iou_thres=0.5,
iou_thres=0.5, conf_thres=0.001,
conf_thres=0.001, nms_thres=0.5,
nms_thres=0.5, save_json=False,
save_json=False, model=None):
model=None # Initialize/load model and set device
):
if model is None: if model is None:
device = torch_utils.select_device() device = torch_utils.select_device()
@ -104,12 +103,10 @@ def test(
box = xyxy2xywh(box) # xywh box = xyxy2xywh(box) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for di, d in enumerate(pred): for di, d in enumerate(pred):
jdict.append({ jdict.append({'image_id': image_id,
'image_id': image_id, 'category_id': coco91class[int(d[6])],
'category_id': coco91class[int(d[6])], 'bbox': [float3(x) for x in box[di]],
'bbox': [float3(x) for x in box[di]], 'score': float(d[4])})
'score': float(d[4])
})
# Assign all predictions as incorrect # Assign all predictions as incorrect
correct = [0] * len(pred) correct = [0] * len(pred)

19
train.py
View File

@ -20,6 +20,8 @@ from utils.utils import *
# 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 # 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
# 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 # 320 --epochs 2 # 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 # 320 --epochs 2
# Training hyperparameters
hyp = {'giou': 0.8541, # giou loss gain hyp = {'giou': 0.8541, # giou loss gain
'xy': 4.062, # xy loss gain 'xy': 4.062, # xy loss gain
'wh': 0.1845, # wh loss gain 'wh': 0.1845, # wh loss gain
@ -34,15 +36,13 @@ hyp = {'giou': 0.8541, # giou loss gain
'weight_decay': 0.000467} # optimizer weight decay 'weight_decay': 0.000467} # optimizer weight decay
def train( def train(cfg,
cfg, data_cfg,
data_cfg, img_size=416,
img_size=416, epochs=100, # 500200 batches at bs 16, 117263 images = 273 epochs
epochs=100, # 500200 batches at bs 16, 117263 images = 273 epochs batch_size=16,
batch_size=16, accumulate=4): # effective bs = batch_size * accumulate = 8 * 8 = 64
accumulate=4, # effective bs = batch_size * accumulate = 8 * 8 = 64 # Initialize
freeze_backbone=False,
):
init_seeds() init_seeds()
weights = 'weights' + os.sep weights = 'weights' + os.sep
latest = weights + 'latest.pt' latest = weights + 'latest.pt'
@ -178,6 +178,7 @@ def train(
scheduler.step() scheduler.step()
# Freeze backbone at epoch 0, unfreeze at epoch 1 (optional) # Freeze backbone at epoch 0, unfreeze at epoch 1 (optional)
freeze_backbone = False
if freeze_backbone and epoch < 2: if freeze_backbone and epoch < 2:
for name, p in model.named_parameters(): for name, p in model.named_parameters():
if int(name.split('.')[1]) < cutoff: # if layer < 75 if int(name.split('.')[1]) < cutoff: # if layer < 75