mirrors
/
yolov5
mirror of https://github.com/ultralytics/yolov5.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge branch 'master' into Maj-Pierre-1

pull/11869/head
Ultralytics Assistant 2024-05-29 22:09:56 +02:00 committed by GitHub
parent 6ac03fa85c 2b7bcf664b
commit 686e54c4d5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
segment/train.py
View File

@ -746,7 +746,7 @@ def run(**kwargs):
""" """
Executes YOLOv5 training with given parameters, altering options programmatically; returns updated options. Executes YOLOv5 training with given parameters, altering options programmatically; returns updated options.
Example: mport train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt') Example: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
""" """
opt = parse_opt(True) opt = parse_opt(True)
for k, v in kwargs.items(): for k, v in kwargs.items():

2
utils/augmentations.py
View File

@ -353,7 +353,7 @@ def classify_albumentations(
if vflip > 0: if vflip > 0:
T += [A.VerticalFlip(p=vflip)] T += [A.VerticalFlip(p=vflip)]
if jitter > 0: if jitter > 0:
color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, satuaration, 0 hue color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, saturation, 0 hue
T += [A.ColorJitter(*color_jitter, 0)] T += [A.ColorJitter(*color_jitter, 0)]
else: # Use fixed crop for eval set (reproducibility) else: # Use fixed crop for eval set (reproducibility)
T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)] T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]

2
utils/dataloaders.py
View File

@ -136,7 +136,7 @@ class SmartDistributedSampler(distributed.DistributedSampler):
g = torch.Generator() g = torch.Generator()
g.manual_seed(self.seed + self.epoch) g.manual_seed(self.seed + self.epoch)
# determine the the eventual size (n) of self.indices (DDP indices) # determine the eventual size (n) of self.indices (DDP indices)
n = int((len(self.dataset) - self.rank - 1) / self.num_replicas) + 1 # num_replicas == WORLD_SIZE n = int((len(self.dataset) - self.rank - 1) / self.num_replicas) + 1 # num_replicas == WORLD_SIZE
idx = torch.randperm(n, generator=g) idx = torch.randperm(n, generator=g)
if not self.shuffle: if not self.shuffle:

2
utils/loggers/clearml/hpo.py
View File

@ -58,7 +58,7 @@ optimizer = HyperParameterOptimizer(
# now we decide if we want to maximize it or minimize it (accuracy we maximize) # now we decide if we want to maximize it or minimize it (accuracy we maximize)
objective_metric_sign="max", objective_metric_sign="max",
# let us limit the number of concurrent experiments, # let us limit the number of concurrent experiments,
# this in turn will make sure we do dont bombard the scheduler with experiments. # this in turn will make sure we don't bombard the scheduler with experiments.
# if we have an auto-scaler connected, this, by proxy, will limit the number of machine # if we have an auto-scaler connected, this, by proxy, will limit the number of machine
max_number_of_concurrent_tasks=1, max_number_of_concurrent_tasks=1,
# this is the optimizer class (actually doing the optimization) # this is the optimizer class (actually doing the optimization)