xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

YOLOv5 updates (#90)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
2022-12-25 14:33:18 +01:00
committed by GitHub
parent ebd3cfb2fd
commit 98815d560f
27 changed files with 281 additions and 161 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/yolo/utils/__init__.py
View File

@ -17,7 +17,7 @@ NUM_THREADS = min(8, max(1, os.cpu_count() - 1)) # number of YOLOv5 multiproces
AUTOINSTALL = str(os.getenv('YOLOv5_AUTOINSTALL', True)).lower() == 'true' # global auto-install mode
FONT = 'Arial.ttf' # https://ultralytics.com/assets/Arial.ttf
VERBOSE = str(os.getenv('YOLOv5_VERBOSE', True)).lower() == 'true' # global verbose mode
TQDM_BAR_FORMAT = '{l_bar}{bar:10}| {n_fmt}/{total_fmt} {elapsed}' # tqdm bar format
TQDM_BAR_FORMAT = '{l_bar}{bar:10}{r_bar}' # tqdm bar format
LOGGING_NAME = 'yolov5'

4
ultralytics/yolo/utils/callbacks/clearml.py
View File

@ -23,9 +23,9 @@ def on_train_start(trainer):
def on_val_end(trainer):
if trainer.epoch == 0:
model_info = {
"Inference speed (ms/img)": round(trainer.validator.speed[1], 1),
"Parameters": get_num_params(trainer.model),
"GFLOPs": round(get_flops(trainer.model), 1),
"Parameters": get_num_params(trainer.model)}
"Inference speed (ms/img)": round(trainer.validator.speed[1], 1)}
Task.current_task().connect(model_info, name='Model')

2
ultralytics/yolo/utils/callbacks/tb.py
View File

@ -11,8 +11,6 @@ def _log_scalars(scalars, step=0):
def on_train_start(trainer):
global writer
writer = SummaryWriter(str(trainer.save_dir))
trainer.console.info(f"Logging results to {trainer.save_dir}\n"
f"Starting training for {trainer.args.epochs} epochs...")
def on_batch_end(trainer):

5
ultralytics/yolo/utils/configs/default.yaml
View File

@ -27,12 +27,13 @@ local_rank: -1
single_cls: False # train multi-class data as single-class
image_weights: False # use weighted image selection for training
rect: False # support rectangular training
cos_lr: False # Use cosine LR scheduler
cos_lr: False # use cosine LR scheduler
close_mosaic: 10 # disable mosaic for final 10 epochs
# Segmentation
overlap_mask: True # masks overlap
mask_ratio: 4 # mask downsample ratio
# Classification
dropout: False # use dropout
dropout: False # use dropout
resume: False

4
ultralytics/yolo/utils/modeling/__init__.py
View File

@ -45,7 +45,7 @@ def attempt_load_weights(weights, device=None, inplace=True, fuse=True):
def parse_model(d, ch): # model_dict, input_channels(3)
# Parse a YOLOv5 model.yaml dictionary
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<50}{'arguments':<30}")
nc, gd, gw, act = d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
if act:
Conv.default_act = eval(act) # redefine default activation, i.e. Conv.default_act = nn.SiLU()
@ -87,7 +87,7 @@ def parse_model(d, ch): # model_dict, input_channels(3)
t = str(m)[8:-2].replace('__main__.', '') # module type
m.np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type = i, f, t # attach index, 'from' index, type
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{m.np:10.0f} {t:<40}{str(args):<30}') # print
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{m.np:10.0f} {t:<50}{str(args):<30}') # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
if i == 0:

79
ultralytics/yolo/utils/ops.py
View File

@ -63,9 +63,9 @@ def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None):
gain = ratio_pad[0][0]
pad = ratio_pad[1]
boxes[:, [0, 2]] -= pad[0] # x padding
boxes[:, [1, 3]] -= pad[1] # y padding
boxes[:, :4] /= gain
boxes[..., [0, 2]] -= pad[0] # x padding
boxes[..., [1, 3]] -= pad[1] # y padding
boxes[..., :4] /= gain
clip_boxes(boxes, img0_shape)
return boxes
@ -73,13 +73,13 @@ def scale_boxes(img1_shape, boxes, img0_shape, ratio_pad=None):
def clip_boxes(boxes, shape):
# Clip boxes (xyxy) to image shape (height, width)
if isinstance(boxes, torch.Tensor): # faster individually
boxes[:, 0].clamp_(0, shape[1]) # x1
boxes[:, 1].clamp_(0, shape[0]) # y1
boxes[:, 2].clamp_(0, shape[1]) # x2
boxes[:, 3].clamp_(0, shape[0]) # y2
boxes[..., 0].clamp_(0, shape[1]) # x1
boxes[..., 1].clamp_(0, shape[0]) # y1
boxes[..., 2].clamp_(0, shape[1]) # x2
boxes[..., 3].clamp_(0, shape[0]) # y2
else: # np.array (faster grouped)
boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2
boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2
boxes[..., [0, 2]] = boxes[..., [0, 2]].clip(0, shape[1]) # x1, x2
boxes[..., [1, 3]] = boxes[..., [1, 3]].clip(0, shape[0]) # y1, y2
def make_divisible(x, divisor):
@ -106,6 +106,9 @@ def non_max_suppression(
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
"""
# Checks
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
if isinstance(prediction, (list, tuple)): # YOLOv5 model in validation model, output = (inference_out, loss_out)
prediction = prediction[0] # select only inference output
@ -118,10 +121,6 @@ def non_max_suppression(
mi = 4 + nc # mask start index
xc = prediction[:, 4:mi].amax(1) > conf_thres # candidates
# Checks
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
# Settings
# min_wh = 2 # (pixels) minimum box width and height
max_wh = 7680 # (pixels) maximum box width and height
@ -172,17 +171,13 @@ def non_max_suppression(
n = x.shape[0] # number of boxes
if not n: # no boxes
continue
elif n > max_nms: # excess boxes
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
else:
x = x[x[:, 4].argsort(descending=True)] # sort by confidence
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence and remove excess boxes
# Batched NMS
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
if i.shape[0] > max_det: # limit detections
i = i[:max_det]
i = i[:max_det] # limit detections
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
@ -244,20 +239,50 @@ def scale_image(im1_shape, masks, im0_shape, ratio_pad=None):
def xyxy2xywh(x):
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
y[:, 2] = x[:, 2] - x[:, 0] # width
y[:, 3] = x[:, 3] - x[:, 1] # height
y[..., 0] = (x[..., 0] + x[..., 2]) / 2 # x center
y[..., 1] = (x[..., 1] + x[..., 3]) / 2 # y center
y[..., 2] = x[..., 2] - x[..., 0] # width
y[..., 3] = x[..., 3] - x[..., 1] # height
return y
def xywh2xyxy(x):
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
y[..., 0] = x[..., 0] - x[..., 2] / 2 # top left x
y[..., 1] = x[..., 1] - x[..., 3] / 2 # top left y
y[..., 2] = x[..., 0] + x[..., 2] / 2 # bottom right x
y[..., 3] = x[..., 1] + x[..., 3] / 2 # bottom right y
return y
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 0] = w * (x[..., 0] - x[..., 2] / 2) + padw # top left x
y[..., 1] = h * (x[..., 1] - x[..., 3] / 2) + padh # top left y
y[..., 2] = w * (x[..., 0] + x[..., 2] / 2) + padw # bottom right x
y[..., 3] = h * (x[..., 1] + x[..., 3] / 2) + padh # bottom right y
return y
def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right
if clip:
clip_boxes(x, (h - eps, w - eps)) # warning: inplace clip
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 0] = ((x[..., 0] + x[..., 2]) / 2) / w # x center
y[..., 1] = ((x[..., 1] + x[..., 3]) / 2) / h # y center
y[..., 2] = (x[..., 2] - x[..., 0]) / w # width
y[..., 3] = (x[..., 3] - x[..., 1]) / h # height
return y
def xyn2xy(x, w=640, h=640, padw=0, padh=0):
# Convert normalized segments into pixel segments, shape (n,2)
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
y[..., 0] = w * x[..., 0] + padw # top left x
y[..., 1] = h * x[..., 1] + padh # top left y
return y

2
ultralytics/yolo/utils/torch_utils.py
View File

@ -29,7 +29,7 @@ WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
@contextmanager
def torch_distributed_zero_first(local_rank: int):
# Decorator to make all processes in distributed training wait for each local_master to do something
if local_rank not in [-1, 0]:
if local_rank not in {-1, 0}:
dist.barrier(device_ids=[local_rank])
yield
if local_rank == 0: