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

Merge remote-tracking branch 'origin/master' 

# Conflicts:
#	.github/ISSUE_TEMPLATE/--bug-report.md
#	.github/workflows/greetings.yml
#	README.md
#	requirements.txt
#	train.py
This commit is contained in:
tomasz 2020-07-02 18:11:14 +02:00
parent 07f4525d0c 63996a8bfe
commit 4219b9fe7d
5 changed files with 337 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

281
cfg/yolov4-tiny.cfg Normal file
View File

@ -0,0 +1,281 @@
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64
subdivisions=1
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
learning_rate=0.00261
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[route]
layers=-1
groups=2
group_id=1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
[route]
layers = -1,-2
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -6,-1
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[route]
layers=-1
groups=2
group_id=1
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[route]
layers = -1,-2
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -6,-1
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[route]
layers=-1
groups=2
group_id=1
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[route]
layers = -1,-2
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -6,-1
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
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
[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=80
num=6
jitter=.3
scale_x_y = 1.05
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
ignore_thresh = .7
truth_thresh = 1
random=0
resize=1.5
nms_kind=greedynms
beta_nms=0.6
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 23
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear
[yolo]
mask = 1,2,3
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=80
num=6
jitter=.3
scale_x_y = 1.05
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
ignore_thresh = .7
truth_thresh = 1
random=0
resize=1.5
nms_kind=greedynms
beta_nms=0.6

2
models.py
View File

@ -438,7 +438,7 @@ def convert(cfg='cfg/yolov3-spp.cfg', weights='weights/yolov3-spp.weights'):
target = weights.rsplit('.', 1)[0] + '.pt'
torch.save(chkpt, target)
print("Success: converted '%s' to 's%'" % (weights, target))
print("Success: converted '%s' to '%s'" % (weights, target))
else:
print('Error: extension not supported.')

6
test.py
View File

@ -23,6 +23,7 @@ def test(cfg,
multi_label=True):
# Initialize/load model and set device
if model is None:
is_training = False
device = torch_utils.select_device(opt.device, batch_size=batch_size)
verbose = opt.task == 'test'
@ -47,6 +48,7 @@ def test(cfg,
if device.type != 'cpu' and torch.cuda.device_count() > 1:
model = nn.DataParallel(model)
else: # called by train.py
is_training = True
device = next(model.parameters()).device # get model device
verbose = False
@ -61,7 +63,7 @@ def test(cfg,
# Dataloader
if dataloader is None:
dataset = LoadImagesAndLabels(path, imgsz, batch_size, rect=True, single_cls=opt.single_cls)
dataset = LoadImagesAndLabels(path, imgsz, batch_size, rect=True, single_cls=opt.single_cls, pad=0.5)
batch_size = min(batch_size, len(dataset))
dataloader = DataLoader(dataset,
batch_size=batch_size,
@ -91,7 +93,7 @@ def test(cfg,
t0 += torch_utils.time_synchronized() - t
# Compute loss
if hasattr(model, 'hyp'): # if model has loss hyperparameters
if is_training: # if model has loss hyperparameters
loss += compute_loss(train_out, targets, model)[1][:3] # GIoU, obj, cls
# Run NMS

48
train.py
View File

@ -66,7 +66,7 @@ def train(hyp):
imgsz_min, imgsz_max, imgsz_test = opt.img_size # img sizes (min, max, test)
# Image Sizes
gs = 64 # (pixels) grid size
gs = 32 # (pixels) grid size
assert math.fmod(imgsz_min, gs) == 0, '--img-size %g must be a %g-multiple' % (imgsz_min, gs)
opt.multi_scale |= imgsz_min != imgsz_max # multi if different (min, max)
if opt.multi_scale:
@ -119,34 +119,49 @@ def train(hyp):
if weights.endswith('.pt'): # pytorch format
print("LOADIN MODEL")
# possible weights are '*.pt', 'yolov3-spp.pt', 'yolov3-tiny.pt' etc.
chkpt = torch.load(weights, map_location=device)
ckpt = torch.load(weights, map_location=device)
# load model
try:
chkpt['model'] = {k: v for k, v in chkpt['model'].items() if model.state_dict()[k].numel() == v.numel()}
model.load_state_dict(chkpt['model'], strict=False)
ckpt['model'] = {k: v for k, v in ckpt['model'].items() if model.state_dict()[k].numel() == v.numel()}
model.load_state_dict(ckpt['model'], strict=False)
except KeyError as e:
s = "%s is not compatible with %s. Specify --weights '' or specify a --cfg compatible with %s. " \
"See https://github.com/ultralytics/yolov3/issues/657" % (opt.weights, opt.cfg, opt.weights)
raise KeyError(s) from e
# load optimizer
if chkpt['optimizer'] is not None:
optimizer.load_state_dict(chkpt['optimizer'])
best_fitness = chkpt['best_fitness']
if ckpt['optimizer'] is not None:
optimizer.load_state_dict(ckpt['optimizer'])
best_fitness = ckpt['best_fitness']
# load results
if chkpt.get('training_results') is not None:
if ckpt.get('training_results') is not None:
with open(results_file, 'w') as file:
file.write(chkpt['training_results']) # write results.txt
file.write(ckpt['training_results']) # write results.txt
start_epoch = chkpt['epoch'] + 1
del chkpt
# epochs
start_epoch = ckpt['epoch'] + 1
if epochs < start_epoch:
print('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
(opt.weights, ckpt['epoch'], epochs))
epochs += ckpt['epoch'] # finetune additional epochs
del ckpt
elif len(weights) > 0: # darknet format
# possible weights are '*.weights', 'yolov3-tiny.conv.15', 'darknet53.conv.74' etc.
load_darknet_weights(model, weights)
if opt.freeze_layers:
output_layer_indices = [idx - 1 for idx, module in enumerate(model.module_list) if isinstance(module, YOLOLayer)]
freeze_layer_indices = [x for x in range(len(model.module_list)) if
(x not in output_layer_indices) and
(x - 1 not in output_layer_indices)]
for idx in freeze_layer_indices:
for parameter in model.module_list[idx].parameters():
parameter.requires_grad_(False)
# Mixed precision training https://github.com/NVIDIA/apex
if mixed_precision:
model, optimizer = amp.initialize(model, optimizer, opt_level='O1', verbosity=0)
@ -343,7 +358,7 @@ def train(hyp):
save = (not opt.nosave) or (final_epoch and not opt.evolve)
if save:
with open(results_file, 'r') as f: # create checkpoint
chkpt = {'epoch': epoch,
ckpt = {'epoch': epoch,
'best_fitness': best_fitness,
'training_results': f.read(),
'model': ema.ema.module.state_dict() if hasattr(model, 'module') else ema.ema.state_dict(),
@ -352,10 +367,10 @@ def train(hyp):
if epoch % opt.save_every_nth_epoch == 0:
torch.save(chkpt, f'yolo_{epoch}.pt')
# Save last, best and delete
torch.save(chkpt, last)
torch.save(ckpt, last)
if (best_fitness == fi) and not final_epoch:
torch.save(chkpt, best)
del chkpt
torch.save(ckpt, best)
del ckpt
# end epoch ----------------------------------------------------------------------------------------------------
@ -400,9 +415,10 @@ if __name__ == '__main__':
parser.add_argument('--device', default='', help='device id (i.e. 0 or 0,1 or cpu)')
parser.add_argument('--adam', action='store_true', help='use adam optimizer')
parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
parser.add_argument('--freeze-layers', action='store_true', help='Freeze non-output layers')
parser.add_argument('--save-every-nth-epoch', type=int, help='Saving every n-th epoth')
opt = parser.parse_args()
#opt.weights = last if opt.resume else opt.weights
#opt.weights = last if opt.resume and not opt.weights else opt.weights
#check_git_status()
opt.cfg = check_file(opt.cfg) # check file
opt.data = check_file(opt.data) # check file

35
utils/datasets.py
View File

@ -18,7 +18,7 @@ from utils.utils import xyxy2xywh, xywh2xyxy
help_url = 'https://github.com/ultralytics/yolov3/wiki/Train-Custom-Data'
img_formats = ['.bmp', '.jpg', '.jpeg', '.png', '.tif', '.dng']
vid_formats = ['.mov', '.avi', '.mp4']
vid_formats = ['.mov', '.avi', '.mp4', '.mpg', '.mpeg', '.m4v', '.wmv', '.mkv']
# Get orientation exif tag
for orientation in ExifTags.TAGS.keys():
@ -62,7 +62,8 @@ class LoadImages: # for inference
self.new_video(videos[0]) # new video
else:
self.cap = None
assert self.nF > 0, 'No images or videos found in ' + path
assert self.nF > 0, 'No images or videos found in %s. Supported formats are:\nimages: %s\nvideos: %s' % \
(path, img_formats, vid_formats)
def __iter__(self):
self.count = 0
@ -256,7 +257,7 @@ class LoadStreams: # multiple IP or RTSP cameras
class LoadImagesAndLabels(Dataset): # for training/testing
def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
cache_images=False, single_cls=False):
cache_images=False, single_cls=False, pad=0.0):
try:
path = str(Path(path)) # os-agnostic
parent = str(Path(path).parent) + os.sep
@ -290,20 +291,22 @@ class LoadImagesAndLabels(Dataset): # for training/testing
self.label_files = [x.replace('images', 'labels').replace(os.path.splitext(x)[-1], '.txt')
for x in self.img_files]
# Read image shapes (wh)
sp = path.replace('.txt', '') + '.shapes' # shapefile path
try:
with open(sp, 'r') as f: # read existing shapefile
s = [x.split() for x in f.read().splitlines()]
assert len(s) == n, 'Shapefile out of sync'
except:
s = [exif_size(Image.open(f)) for f in tqdm(self.img_files, desc='Reading image shapes')]
np.savetxt(sp, s, fmt='%g') # overwrites existing (if any)
self.shapes = np.array(s, dtype=np.float64)
# Rectangular Training https://github.com/ultralytics/yolov3/issues/232
if self.rect:
# Read image shapes (wh)
sp = path.replace('.txt', '') + '.shapes' # shapefile path
try:
with open(sp, 'r') as f: # read existing shapefile
s = [x.split() for x in f.read().splitlines()]
assert len(s) == n, 'Shapefile out of sync'
except:
s = [exif_size(Image.open(f)) for f in tqdm(self.img_files, desc='Reading image shapes')]
np.savetxt(sp, s, fmt='%g') # overwrites existing (if any)
# Sort by aspect ratio
s = np.array(s, dtype=np.float64)
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio
irect = ar.argsort()
self.img_files = [self.img_files[i] for i in irect]
@ -321,7 +324,7 @@ class LoadImagesAndLabels(Dataset): # for training/testing
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(np.array(shapes) * img_size / 64.).astype(np.int) * 64
self.batch_shapes = np.ceil(np.array(shapes) * img_size / 32. + pad).astype(np.int) * 32
# Cache labels
self.imgs = [None] * n
@ -529,7 +532,7 @@ def load_image(self, index):
assert img is not None, 'Image Not Found ' + path
h0, w0 = img.shape[:2] # orig hw
r = self.img_size / max(h0, w0) # resize image to img_size
if r < 1 or (self.augment and r != 1): # always resize down, only resize up if training with augmentation
if r != 1: # always resize down, only resize up if training with augmentation
interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR
img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp)
return img, (h0, w0), img.shape[:2] # img, hw_original, hw_resized