Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity

Update Actions with Lychee and GitHub Token (#12592)

Browse Source 
* Add Ultralytics Actions

* Auto-format by Ultralytics actions

* Update format.yml

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

---------

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Paula DerrengerUltralyticsAssistantGlenn Jocher
 authored and GitHub committed 2024-01-08 01:29:14 +01:00
1 parent f56355d321
commit ad97dc6a6d
47 files changed
+4217 -3462
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

segment/train.py
+299 -219
View File
@@ -1,7 +1,7 @@
# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license
"""
Train a YOLOv5 segment model on a segment dataset
Models and datasets download automatically from the latest YOLOv5 release.
Train a YOLOv5 segment model on a segment dataset Models and datasets download automatically from the latest YOLOv5
release.
Usage - Single-GPU training:
$ python segment/train.py --data coco128-seg.yaml --weights yolov5s-seg.pt --img 640 # from pretrained (recommended)
@@ -47,47 +47,104 @@ from utils.autoanchor import check_anchors
from utils.autobatch import check_train_batch_size
from utils.callbacks import Callbacks
from utils.downloads import attempt_download, is_url
from utils.general import (LOGGER, TQDM_BAR_FORMAT, check_amp, check_dataset, check_file, check_git_info,
check_git_status, check_img_size, check_requirements, check_suffix, check_yaml, colorstr,
get_latest_run, increment_path, init_seeds, intersect_dicts, labels_to_class_weights,
labels_to_image_weights, one_cycle, print_args, print_mutation, strip_optimizer, yaml_save)
from utils.general import (
LOGGER,
TQDM_BAR_FORMAT,
check_amp,
check_dataset,
check_file,
check_git_info,
check_git_status,
check_img_size,
check_requirements,
check_suffix,
check_yaml,
colorstr,
get_latest_run,
increment_path,
init_seeds,
intersect_dicts,
labels_to_class_weights,
labels_to_image_weights,
one_cycle,
print_args,
print_mutation,
strip_optimizer,
yaml_save,
)
from utils.loggers import GenericLogger
from utils.plots import plot_evolve, plot_labels
from utils.segment.dataloaders import create_dataloader
from utils.segment.loss import ComputeLoss
from utils.segment.metrics import KEYS, fitness
from utils.segment.plots import plot_images_and_masks, plot_results_with_masks
from utils.torch_utils import (EarlyStopping, ModelEMA, de_parallel, select_device, smart_DDP, smart_optimizer,
smart_resume, torch_distributed_zero_first)
from utils.torch_utils import (
EarlyStopping,
ModelEMA,
de_parallel,
select_device,
smart_DDP,
smart_optimizer,
smart_resume,
torch_distributed_zero_first,
)
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
RANK = int(os.getenv('RANK', -1))
WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
LOCAL_RANK = int(os.getenv("LOCAL_RANK", -1)) # https://pytorch.org/docs/stable/elastic/run.html
RANK = int(os.getenv("RANK", -1))
WORLD_SIZE = int(os.getenv("WORLD_SIZE", 1))
GIT_INFO = check_git_info()
def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictionary
save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze, mask_ratio = \
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze, opt.mask_ratio
(
save_dir,
epochs,
batch_size,
weights,
single_cls,
evolve,
data,
cfg,
resume,
noval,
nosave,
workers,
freeze,
mask_ratio,
) = (
Path(opt.save_dir),
opt.epochs,
opt.batch_size,
opt.weights,
opt.single_cls,
opt.evolve,
opt.data,
opt.cfg,
opt.resume,
opt.noval,
opt.nosave,
opt.workers,
opt.freeze,
opt.mask_ratio,
)
# callbacks.run('on_pretrain_routine_start')
# Directories
w = save_dir / 'weights' # weights dir
w = save_dir / "weights" # weights dir
(w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir
last, best = w / 'last.pt', w / 'best.pt'
last, best = w / "last.pt", w / "best.pt"
# Hyperparameters
if isinstance(hyp, str):
with open(hyp, errors='ignore') as f:
with open(hyp, errors="ignore") as f:
hyp = yaml.safe_load(f) # load hyps dict
LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
LOGGER.info(colorstr("hyperparameters: ") + ", ".join(f"{k}={v}" for k, v in hyp.items()))
opt.hyp = hyp.copy() # for saving hyps to checkpoints
# Save run settings
if not evolve:
yaml_save(save_dir / 'hyp.yaml', hyp)
yaml_save(save_dir / 'opt.yaml', vars(opt))
yaml_save(save_dir / "hyp.yaml", hyp)
yaml_save(save_dir / "opt.yaml", vars(opt))
# Loggers
data_dict = None
@@ -97,39 +154,39 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Config
plots = not evolve and not opt.noplots # create plots
overlap = not opt.no_overlap
cuda = device.type != 'cpu'
cuda = device.type != "cpu"
init_seeds(opt.seed + 1 + RANK, deterministic=True)
with torch_distributed_zero_first(LOCAL_RANK):
data_dict = data_dict or check_dataset(data) # check if None
train_path, val_path = data_dict['train'], data_dict['val']
nc = 1 if single_cls else int(data_dict['nc']) # number of classes
names = {0: 'item'} if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt') # COCO dataset
train_path, val_path = data_dict["train"], data_dict["val"]
nc = 1 if single_cls else int(data_dict["nc"]) # number of classes
names = {0: "item"} if single_cls and len(data_dict["names"]) != 1 else data_dict["names"] # class names
is_coco = isinstance(val_path, str) and val_path.endswith("coco/val2017.txt") # COCO dataset
# Model
check_suffix(weights, '.pt') # check weights
pretrained = weights.endswith('.pt')
check_suffix(weights, ".pt") # check weights
pretrained = weights.endswith(".pt")
if pretrained:
with torch_distributed_zero_first(LOCAL_RANK):
weights = attempt_download(weights) # download if not found locally
ckpt = torch.load(weights, map_location='cpu') # load checkpoint to CPU to avoid CUDA memory leak
model = SegmentationModel(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)
exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
ckpt = torch.load(weights, map_location="cpu") # load checkpoint to CPU to avoid CUDA memory leak
model = SegmentationModel(cfg or ckpt["model"].yaml, ch=3, nc=nc, anchors=hyp.get("anchors")).to(device)
exclude = ["anchor"] if (cfg or hyp.get("anchors")) and not resume else [] # exclude keys
csd = ckpt["model"].float().state_dict() # checkpoint state_dict as FP32
csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect
model.load_state_dict(csd, strict=False) # load
LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report
LOGGER.info(f"Transferred {len(csd)}/{len(model.state_dict())} items from {weights}") # report
else:
model = SegmentationModel(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
model = SegmentationModel(cfg, ch=3, nc=nc, anchors=hyp.get("anchors")).to(device) # create
amp = check_amp(model) # check AMP
# Freeze
freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))] # layers to freeze
freeze = [f"model.{x}." for x in (freeze if len(freeze) > 1 else range(freeze[0]))] # layers to freeze
for k, v in model.named_parameters():
v.requires_grad = True # train all layers
# v.register_hook(lambda x: torch.nan_to_num(x)) # NaN to 0 (commented for erratic training results)
if any(x in k for x in freeze):
LOGGER.info(f'freezing {k}')
LOGGER.info(f"freezing {k}")
v.requires_grad = False
# Image size
@@ -139,20 +196,20 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Batch size
if RANK == -1 and batch_size == -1: # single-GPU only, estimate best batch size
batch_size = check_train_batch_size(model, imgsz, amp)
logger.update_params({'batch_size': batch_size})
logger.update_params({"batch_size": batch_size})
# loggers.on_params_update({"batch_size": batch_size})
# Optimizer
nbs = 64 # nominal batch size
accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing
hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay
optimizer = smart_optimizer(model, opt.optimizer, hyp['lr0'], hyp['momentum'], hyp['weight_decay'])
hyp["weight_decay"] *= batch_size * accumulate / nbs # scale weight_decay
optimizer = smart_optimizer(model, opt.optimizer, hyp["lr0"], hyp["momentum"], hyp["weight_decay"])
# Scheduler
if opt.cos_lr:
lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf']
lf = one_cycle(1, hyp["lrf"], epochs) # cosine 1->hyp['lrf']
else:
lf = lambda x: (1 - x / epochs) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear
lf = lambda x: (1 - x / epochs) * (1.0 - hyp["lrf"]) + hyp["lrf"] # linear
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs)
# EMA
@@ -168,15 +225,15 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# DP mode
if cuda and RANK == -1 and torch.cuda.device_count() > 1:
LOGGER.warning(
'WARNING ⚠️ DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n'
'See Multi-GPU Tutorial at https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training to get started.'
"WARNING ⚠️ DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n"
"See Multi-GPU Tutorial at https://docs.ultralytics.com/yolov5/tutorials/multi_gpu_training to get started."
)
model = torch.nn.DataParallel(model)
# SyncBatchNorm
if opt.sync_bn and cuda and RANK != -1:
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
LOGGER.info('Using SyncBatchNorm()')
LOGGER.info("Using SyncBatchNorm()")
# Trainloader
train_loader, dataset = create_dataloader(
@@ -187,41 +244,43 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
single_cls,
hyp=hyp,
augment=True,
cache=None if opt.cache == 'val' else opt.cache,
cache=None if opt.cache == "val" else opt.cache,
rect=opt.rect,
rank=LOCAL_RANK,
workers=workers,
image_weights=opt.image_weights,
quad=opt.quad,
prefix=colorstr('train: '),
prefix=colorstr("train: "),
shuffle=True,
mask_downsample_ratio=mask_ratio,
overlap_mask=overlap,
)
labels = np.concatenate(dataset.labels, 0)
mlc = int(labels[:, 0].max()) # max label class
assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}'
assert mlc < nc, f"Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}"
# Process 0
if RANK in {-1, 0}:
val_loader = create_dataloader(val_path,
imgsz,
batch_size // WORLD_SIZE * 2,
gs,
single_cls,
hyp=hyp,
cache=None if noval else opt.cache,
rect=True,
rank=-1,
workers=workers * 2,
pad=0.5,
mask_downsample_ratio=mask_ratio,
overlap_mask=overlap,
prefix=colorstr('val: '))[0]
val_loader = create_dataloader(
val_path,
imgsz,
batch_size // WORLD_SIZE * 2,
gs,
single_cls,
hyp=hyp,
cache=None if noval else opt.cache,
rect=True,
rank=-1,
workers=workers * 2,
pad=0.5,
mask_downsample_ratio=mask_ratio,
overlap_mask=overlap,
prefix=colorstr("val: "),
)[0]
if not resume:
if not opt.noautoanchor:
check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz) # run AutoAnchor
check_anchors(dataset, model=model, thr=hyp["anchor_t"], imgsz=imgsz) # run AutoAnchor
model.half().float() # pre-reduce anchor precision
if plots:
@@ -234,10 +293,10 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Model attributes
nl = de_parallel(model).model[-1].nl # number of detection layers (to scale hyps)
hyp['box'] *= 3 / nl # scale to layers
hyp['cls'] *= nc / 80 * 3 / nl # scale to classes and layers
hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
hyp['label_smoothing'] = opt.label_smoothing
hyp["box"] *= 3 / nl # scale to layers
hyp["cls"] *= nc / 80 * 3 / nl # scale to classes and layers
hyp["obj"] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
hyp["label_smoothing"] = opt.label_smoothing
model.nc = nc # attach number of classes to model
model.hyp = hyp # attach hyperparameters to model
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights
@@ -246,7 +305,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Start training
t0 = time.time()
nb = len(train_loader) # number of batches
nw = max(round(hyp['warmup_epochs'] * nb), 100) # number of warmup iterations, max(3 epochs, 100 iterations)
nw = max(round(hyp["warmup_epochs"] * nb), 100) # number of warmup iterations, max(3 epochs, 100 iterations)
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
last_opt_step = -1
maps = np.zeros(nc) # mAP per class
@@ -256,10 +315,12 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
stopper, stop = EarlyStopping(patience=opt.patience), False
compute_loss = ComputeLoss(model, overlap=overlap) # init loss class
# callbacks.run('on_train_start')
LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
f"Logging results to {colorstr('bold', save_dir)}\n"
f'Starting training for {epochs} epochs...')
LOGGER.info(
f'Image sizes {imgsz} train, {imgsz} val\n'
f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
f"Logging results to {colorstr('bold', save_dir)}\n"
f'Starting training for {epochs} epochs...'
)
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
# callbacks.run('on_train_epoch_start')
model.train()
@@ -278,8 +339,10 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
if RANK != -1:
train_loader.sampler.set_epoch(epoch)
pbar = enumerate(train_loader)
LOGGER.info(('\n' + '%11s' * 8) %
('Epoch', 'GPU_mem', 'box_loss', 'seg_loss', 'obj_loss', 'cls_loss', 'Instances', 'Size'))
LOGGER.info(
("\n" + "%11s" * 8)
% ("Epoch", "GPU_mem", "box_loss", "seg_loss", "obj_loss", "cls_loss", "Instances", "Size")
)
if RANK in {-1, 0}:
pbar = tqdm(pbar, total=nb, bar_format=TQDM_BAR_FORMAT) # progress bar
optimizer.zero_grad()
@@ -295,9 +358,9 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round())
for j, x in enumerate(optimizer.param_groups):
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 0 else 0.0, x['initial_lr'] * lf(epoch)])
if 'momentum' in x:
x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
x["lr"] = np.interp(ni, xi, [hyp["warmup_bias_lr"] if j == 0 else 0.0, x["initial_lr"] * lf(epoch)])
if "momentum" in x:
x["momentum"] = np.interp(ni, xi, [hyp["warmup_momentum"], hyp["momentum"]])
# Multi-scale
if opt.multi_scale:
@@ -305,7 +368,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
sf = sz / max(imgs.shape[2:]) # scale factor
if sf != 1:
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple)
imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
imgs = nn.functional.interpolate(imgs, size=ns, mode="bilinear", align_corners=False)
# Forward
with torch.cuda.amp.autocast(amp):
@@ -314,7 +377,7 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
if RANK != -1:
loss *= WORLD_SIZE # gradient averaged between devices in DDP mode
if opt.quad:
loss *= 4.
loss *= 4.0
# Backward
scaler.scale(loss).backward()
@@ -333,9 +396,11 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Log
if RANK in {-1, 0}:
mloss = (mloss * i + loss_items) / (i + 1) # update mean losses
mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB)
pbar.set_description(('%11s' * 2 + '%11.4g' * 6) %
(f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
mem = f"{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G" # (GB)
pbar.set_description(
("%11s" * 2 + "%11.4g" * 6)
% (f"{epoch}/{epochs - 1}", mem, *mloss, targets.shape[0], imgs.shape[-1])
)
# callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths)
# if callbacks.stop_training:
# return
@@ -343,35 +408,37 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Mosaic plots
if plots:
if ni < 3:
plot_images_and_masks(imgs, targets, masks, paths, save_dir / f'train_batch{ni}.jpg')
plot_images_and_masks(imgs, targets, masks, paths, save_dir / f"train_batch{ni}.jpg")
if ni == 10:
files = sorted(save_dir.glob('train*.jpg'))
logger.log_images(files, 'Mosaics', epoch)
files = sorted(save_dir.glob("train*.jpg"))
logger.log_images(files, "Mosaics", epoch)
# end batch ------------------------------------------------------------------------------------------------
# Scheduler
lr = [x['lr'] for x in optimizer.param_groups] # for loggers
lr = [x["lr"] for x in optimizer.param_groups] # for loggers
scheduler.step()
if RANK in {-1, 0}:
# mAP
# callbacks.run('on_train_epoch_end', epoch=epoch)
ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
ema.update_attr(model, include=["yaml", "nc", "hyp", "names", "stride", "class_weights"])
final_epoch = (epoch + 1 == epochs) or stopper.possible_stop
if not noval or final_epoch: # Calculate mAP
results, maps, _ = validate.run(data_dict,
batch_size=batch_size // WORLD_SIZE * 2,
imgsz=imgsz,
half=amp,
model=ema.ema,
single_cls=single_cls,
dataloader=val_loader,
save_dir=save_dir,
plots=False,
callbacks=callbacks,
compute_loss=compute_loss,
mask_downsample_ratio=mask_ratio,
overlap=overlap)
results, maps, _ = validate.run(
data_dict,
batch_size=batch_size // WORLD_SIZE * 2,
imgsz=imgsz,
half=amp,
model=ema.ema,
single_cls=single_cls,
dataloader=val_loader,
save_dir=save_dir,
plots=False,
callbacks=callbacks,
compute_loss=compute_loss,
mask_downsample_ratio=mask_ratio,
overlap=overlap,
)
# Update best mAP
fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
@@ -387,23 +454,24 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# Save model
if (not nosave) or (final_epoch and not evolve): # if save
ckpt = {
'epoch': epoch,
'best_fitness': best_fitness,
'model': deepcopy(de_parallel(model)).half(),
'ema': deepcopy(ema.ema).half(),
'updates': ema.updates,
'optimizer': optimizer.state_dict(),
'opt': vars(opt),
'git': GIT_INFO, # {remote, branch, commit} if a git repo
'date': datetime.now().isoformat()}
"epoch": epoch,
"best_fitness": best_fitness,
"model": deepcopy(de_parallel(model)).half(),
"ema": deepcopy(ema.ema).half(),
"updates": ema.updates,
"optimizer": optimizer.state_dict(),
"opt": vars(opt),
"git": GIT_INFO, # {remote, branch, commit} if a git repo
"date": datetime.now().isoformat(),
}
# Save last, best and delete
torch.save(ckpt, last)
if best_fitness == fi:
torch.save(ckpt, best)
if opt.save_period > 0 and epoch % opt.save_period == 0:
torch.save(ckpt, w / f'epoch{epoch}.pt')
logger.log_model(w / f'epoch{epoch}.pt')
torch.save(ckpt, w / f"epoch{epoch}.pt")
logger.log_model(w / f"epoch{epoch}.pt")
del ckpt
# callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi)
@@ -419,12 +487,12 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
# end epoch ----------------------------------------------------------------------------------------------------
# end training -----------------------------------------------------------------------------------------------------
if RANK in {-1, 0}:
LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.')
LOGGER.info(f"\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.")
for f in last, best:
if f.exists():
strip_optimizer(f) # strip optimizers
if f is best:
LOGGER.info(f'\nValidating {f}...')
LOGGER.info(f"\nValidating {f}...")
results, _, _ = validate.run(
data_dict,
batch_size=batch_size // WORLD_SIZE * 2,
@@ -440,7 +508,8 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
callbacks=callbacks,
compute_loss=compute_loss,
mask_downsample_ratio=mask_ratio,
overlap=overlap) # val best model with plots
overlap=overlap,
) # val best model with plots
if is_coco:
# callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi)
metrics_dict = dict(zip(KEYS, list(mloss) + list(results) + lr))
@@ -452,56 +521,56 @@ def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictio
if not opt.evolve:
logger.log_model(best, epoch)
if plots:
plot_results_with_masks(file=save_dir / 'results.csv') # save results.png
files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))]
plot_results_with_masks(file=save_dir / "results.csv") # save results.png
files = ["results.png", "confusion_matrix.png", *(f"{x}_curve.png" for x in ("F1", "PR", "P", "R"))]
files = [(save_dir / f) for f in files if (save_dir / f).exists()] # filter
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
logger.log_images(files, 'Results', epoch + 1)
logger.log_images(sorted(save_dir.glob('val*.jpg')), 'Validation', epoch + 1)
logger.log_images(files, "Results", epoch + 1)
logger.log_images(sorted(save_dir.glob("val*.jpg")), "Validation", epoch + 1)
torch.cuda.empty_cache()
return results
def parse_opt(known=False):
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s-seg.pt', help='initial weights path')
parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128-seg.yaml', help='dataset.yaml path')
parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
parser.add_argument('--epochs', type=int, default=100, help='total training epochs')
parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
parser.add_argument('--rect', action='store_true', help='rectangular training')
parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
parser.add_argument('--noval', action='store_true', help='only validate final epoch')
parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
parser.add_argument('--noplots', action='store_true', help='save no plot files')
parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache', type=str, nargs='?', const='ram', help='image --cache ram/disk')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
parser.add_argument('--project', default=ROOT / 'runs/train-seg', help='save to project/name')
parser.add_argument('--name', default='exp', help='save to project/name')
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
parser.add_argument('--quad', action='store_true', help='quad dataloader')
parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
parser.add_argument('--seed', type=int, default=0, help='Global training seed')
parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')
parser.add_argument("--weights", type=str, default=ROOT / "yolov5s-seg.pt", help="initial weights path")
parser.add_argument("--cfg", type=str, default="", help="model.yaml path")
parser.add_argument("--data", type=str, default=ROOT / "data/coco128-seg.yaml", help="dataset.yaml path")
parser.add_argument("--hyp", type=str, default=ROOT / "data/hyps/hyp.scratch-low.yaml", help="hyperparameters path")
parser.add_argument("--epochs", type=int, default=100, help="total training epochs")
parser.add_argument("--batch-size", type=int, default=16, help="total batch size for all GPUs, -1 for autobatch")
parser.add_argument("--imgsz", "--img", "--img-size", type=int, default=640, help="train, val image size (pixels)")
parser.add_argument("--rect", action="store_true", help="rectangular training")
parser.add_argument("--resume", nargs="?", const=True, default=False, help="resume most recent training")
parser.add_argument("--nosave", action="store_true", help="only save final checkpoint")
parser.add_argument("--noval", action="store_true", help="only validate final epoch")
parser.add_argument("--noautoanchor", action="store_true", help="disable AutoAnchor")
parser.add_argument("--noplots", action="store_true", help="save no plot files")
parser.add_argument("--evolve", type=int, nargs="?", const=300, help="evolve hyperparameters for x generations")
parser.add_argument("--bucket", type=str, default="", help="gsutil bucket")
parser.add_argument("--cache", type=str, nargs="?", const="ram", help="image --cache ram/disk")
parser.add_argument("--image-weights", action="store_true", help="use weighted image selection for training")
parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu")
parser.add_argument("--multi-scale", action="store_true", help="vary img-size +/- 50%%")
parser.add_argument("--single-cls", action="store_true", help="train multi-class data as single-class")
parser.add_argument("--optimizer", type=str, choices=["SGD", "Adam", "AdamW"], default="SGD", help="optimizer")
parser.add_argument("--sync-bn", action="store_true", help="use SyncBatchNorm, only available in DDP mode")
parser.add_argument("--workers", type=int, default=8, help="max dataloader workers (per RANK in DDP mode)")
parser.add_argument("--project", default=ROOT / "runs/train-seg", help="save to project/name")
parser.add_argument("--name", default="exp", help="save to project/name")
parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment")
parser.add_argument("--quad", action="store_true", help="quad dataloader")
parser.add_argument("--cos-lr", action="store_true", help="cosine LR scheduler")
parser.add_argument("--label-smoothing", type=float, default=0.0, help="Label smoothing epsilon")
parser.add_argument("--patience", type=int, default=100, help="EarlyStopping patience (epochs without improvement)")
parser.add_argument("--freeze", nargs="+", type=int, default=[0], help="Freeze layers: backbone=10, first3=0 1 2")
parser.add_argument("--save-period", type=int, default=-1, help="Save checkpoint every x epochs (disabled if < 1)")
parser.add_argument("--seed", type=int, default=0, help="Global training seed")
parser.add_argument("--local_rank", type=int, default=-1, help="Automatic DDP Multi-GPU argument, do not modify")
# Instance Segmentation Args
parser.add_argument('--mask-ratio', type=int, default=4, help='Downsample the truth masks to saving memory')
parser.add_argument('--no-overlap', action='store_true', help='Overlap masks train faster at slightly less mAP')
parser.add_argument("--mask-ratio", type=int, default=4, help="Downsample the truth masks to saving memory")
parser.add_argument("--no-overlap", action="store_true", help="Overlap masks train faster at slightly less mAP")
return parser.parse_known_args()[0] if known else parser.parse_args()
@@ -511,46 +580,51 @@ def main(opt, callbacks=Callbacks()):
if RANK in {-1, 0}:
print_args(vars(opt))
check_git_status()
check_requirements(ROOT / 'requirements.txt')
check_requirements(ROOT / "requirements.txt")
# Resume
if opt.resume and not opt.evolve: # resume from specified or most recent last.pt
last = Path(check_file(opt.resume) if isinstance(opt.resume, str) else get_latest_run())
opt_yaml = last.parent.parent / 'opt.yaml' # train options yaml
opt_yaml = last.parent.parent / "opt.yaml" # train options yaml
opt_data = opt.data # original dataset
if opt_yaml.is_file():
with open(opt_yaml, errors='ignore') as f:
with open(opt_yaml, errors="ignore") as f:
d = yaml.safe_load(f)
else:
d = torch.load(last, map_location='cpu')['opt']
d = torch.load(last, map_location="cpu")["opt"]
opt = argparse.Namespace(**d) # replace
opt.cfg, opt.weights, opt.resume = '', str(last), True # reinstate
opt.cfg, opt.weights, opt.resume = "", str(last), True # reinstate
if is_url(opt_data):
opt.data = check_file(opt_data) # avoid HUB resume auth timeout
else:
opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \
check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks
assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = (
check_file(opt.data),
check_yaml(opt.cfg),
check_yaml(opt.hyp),
str(opt.weights),
str(opt.project),
) # checks
assert len(opt.cfg) or len(opt.weights), "either --cfg or --weights must be specified"
if opt.evolve:
if opt.project == str(ROOT / 'runs/train-seg'): # if default project name, rename to runs/evolve-seg
opt.project = str(ROOT / 'runs/evolve-seg')
if opt.project == str(ROOT / "runs/train-seg"): # if default project name, rename to runs/evolve-seg
opt.project = str(ROOT / "runs/evolve-seg")
opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume
if opt.name == 'cfg':
if opt.name == "cfg":
opt.name = Path(opt.cfg).stem # use model.yaml as name
opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))
# DDP mode
device = select_device(opt.device, batch_size=opt.batch_size)
if LOCAL_RANK != -1:
msg = 'is not compatible with YOLOv5 Multi-GPU DDP training'
assert not opt.image_weights, f'--image-weights {msg}'
assert not opt.evolve, f'--evolve {msg}'
assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size'
assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE'
assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
msg = "is not compatible with YOLOv5 Multi-GPU DDP training"
assert not opt.image_weights, f"--image-weights {msg}"
assert not opt.evolve, f"--evolve {msg}"
assert opt.batch_size != -1, f"AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size"
assert opt.batch_size % WORLD_SIZE == 0, f"--batch-size {opt.batch_size} must be multiple of WORLD_SIZE"
assert torch.cuda.device_count() > LOCAL_RANK, "insufficient CUDA devices for DDP command"
torch.cuda.set_device(LOCAL_RANK)
device = torch.device('cuda', LOCAL_RANK)
dist.init_process_group(backend='nccl' if dist.is_nccl_available() else 'gloo')
device = torch.device("cuda", LOCAL_RANK)
dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
# Train
if not opt.evolve:
@@ -560,65 +634,69 @@ def main(opt, callbacks=Callbacks()):
else:
# Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
meta = {
'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
'weight_decay': (1, 0.0, 0.001), # optimizer weight decay
'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok)
'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum
'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr
'box': (1, 0.02, 0.2), # box loss gain
'cls': (1, 0.2, 4.0), # cls loss gain
'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight
'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels)
'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight
'iou_t': (0, 0.1, 0.7), # IoU training threshold
'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold
'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
'degrees': (1, 0.0, 45.0), # image rotation (+/- deg)
'translate': (1, 0.0, 0.9), # image translation (+/- fraction)
'scale': (1, 0.0, 0.9), # image scale (+/- gain)
'shear': (1, 0.0, 10.0), # image shear (+/- deg)
'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
'flipud': (1, 0.0, 1.0), # image flip up-down (probability)
'fliplr': (0, 0.0, 1.0), # image flip left-right (probability)
'mosaic': (1, 0.0, 1.0), # image mixup (probability)
'mixup': (1, 0.0, 1.0), # image mixup (probability)
'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability)
"lr0": (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3)
"lrf": (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf)
"momentum": (0.3, 0.6, 0.98), # SGD momentum/Adam beta1
"weight_decay": (1, 0.0, 0.001), # optimizer weight decay
"warmup_epochs": (1, 0.0, 5.0), # warmup epochs (fractions ok)
"warmup_momentum": (1, 0.0, 0.95), # warmup initial momentum
"warmup_bias_lr": (1, 0.0, 0.2), # warmup initial bias lr
"box": (1, 0.02, 0.2), # box loss gain
"cls": (1, 0.2, 4.0), # cls loss gain
"cls_pw": (1, 0.5, 2.0), # cls BCELoss positive_weight
"obj": (1, 0.2, 4.0), # obj loss gain (scale with pixels)
"obj_pw": (1, 0.5, 2.0), # obj BCELoss positive_weight
"iou_t": (0, 0.1, 0.7), # IoU training threshold
"anchor_t": (1, 2.0, 8.0), # anchor-multiple threshold
"anchors": (2, 2.0, 10.0), # anchors per output grid (0 to ignore)
"fl_gamma": (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5)
"hsv_h": (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction)
"hsv_s": (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction)
"hsv_v": (1, 0.0, 0.9), # image HSV-Value augmentation (fraction)
"degrees": (1, 0.0, 45.0), # image rotation (+/- deg)
"translate": (1, 0.0, 0.9), # image translation (+/- fraction)
"scale": (1, 0.0, 0.9), # image scale (+/- gain)
"shear": (1, 0.0, 10.0), # image shear (+/- deg)
"perspective": (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
"flipud": (1, 0.0, 1.0), # image flip up-down (probability)
"fliplr": (0, 0.0, 1.0), # image flip left-right (probability)
"mosaic": (1, 0.0, 1.0), # image mixup (probability)
"mixup": (1, 0.0, 1.0), # image mixup (probability)
"copy_paste": (1, 0.0, 1.0),
} # segment copy-paste (probability)
with open(opt.hyp, errors='ignore') as f:
with open(opt.hyp, errors="ignore") as f:
hyp = yaml.safe_load(f) # load hyps dict
if 'anchors' not in hyp: # anchors commented in hyp.yaml
hyp['anchors'] = 3
if "anchors" not in hyp: # anchors commented in hyp.yaml
hyp["anchors"] = 3
if opt.noautoanchor:
del hyp['anchors'], meta['anchors']
del hyp["anchors"], meta["anchors"]
opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv'
evolve_yaml, evolve_csv = save_dir / "hyp_evolve.yaml", save_dir / "evolve.csv"
if opt.bucket:
# download evolve.csv if exists
subprocess.run([
'gsutil',
'cp',
f'gs://{opt.bucket}/evolve.csv',
str(evolve_csv), ])
subprocess.run(
[
"gsutil",
"cp",
f"gs://{opt.bucket}/evolve.csv",
str(evolve_csv),
]
)
for _ in range(opt.evolve): # generations to evolve
if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate
# Select parent(s)
parent = 'single' # parent selection method: 'single' or 'weighted'
x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1)
parent = "single" # parent selection method: 'single' or 'weighted'
x = np.loadtxt(evolve_csv, ndmin=2, delimiter=",", skiprows=1)
n = min(5, len(x)) # number of previous results to consider
x = x[np.argsort(-fitness(x))][:n] # top n mutations
w = fitness(x) - fitness(x).min() + 1E-6 # weights (sum > 0)
if parent == 'single' or len(x) == 1:
w = fitness(x) - fitness(x).min() + 1e-6 # weights (sum > 0)
if parent == "single" or len(x) == 1:
# x = x[random.randint(0, n - 1)] # random selection
x = x[random.choices(range(n), weights=w)[0]] # weighted selection
elif parent == 'weighted':
elif parent == "weighted":
x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination
# Mutate
@@ -647,9 +725,11 @@ def main(opt, callbacks=Callbacks()):
# Plot results
plot_evolve(evolve_csv)
LOGGER.info(f'Hyperparameter evolution finished {opt.evolve} generations\n'
f"Results saved to {colorstr('bold', save_dir)}\n"
f'Usage example: $ python train.py --hyp {evolve_yaml}')
LOGGER.info(
f'Hyperparameter evolution finished {opt.evolve} generations\n'
f"Results saved to {colorstr('bold', save_dir)}\n"
f'Usage example: $ python train.py --hyp {evolve_yaml}'
)
def run(**kwargs):
@@ -661,6 +741,6 @@ def run(**kwargs):
return opt
if __name__ == '__main__':
if __name__ == "__main__":
opt = parse_opt()
main(opt)