Ankle/yolov5_birdproject
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Unified '/project/name' results saving (#1377)

Browse Source 
* Project/name update

* Update ci-testing.yml

* address project with path separator failure mode

* Project/name update

* address project with path separator failure mode

* Update ci-testing.yml

* detect.py default --name bug fix

* missing rstrip PR

* train/exp0 to train/exp
This commit is contained in:
Glenn Jocher authored and GitHub committed 2020-11-12 23:37:46 +01:00
1 parent 04081f8102
commit c4addd7761
7 files changed
+71 -78
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

train.py
+30 -27
View File
@@ -27,7 +27,7 @@ from utils.datasets import create_dataloader
from utils.general import (
torch_distributed_zero_first, labels_to_class_weights, plot_labels, check_anchors, labels_to_image_weights,
compute_loss, plot_images, fitness, strip_optimizer, plot_results, get_latest_run, check_dataset, check_file,
check_git_status, check_img_size, increment_dir, print_mutation, plot_evolution, set_logging, init_seeds)
check_git_status, check_img_size, increment_path, print_mutation, plot_evolution, set_logging, init_seeds)
from utils.google_utils import attempt_download
from utils.torch_utils import ModelEMA, select_device, intersect_dicts
@@ -36,19 +36,20 @@ logger = logging.getLogger(__name__)
def train(hyp, opt, device, tb_writer=None, wandb=None):
logger.info(f'Hyperparameters {hyp}')
log_dir = Path(tb_writer.log_dir) if tb_writer else Path(opt.logdir) / 'evolve' # logging directory
wdir = log_dir / 'weights' # weights directory
wdir.mkdir(parents=True, exist_ok=True)
save_dir, epochs, batch_size, total_batch_size, weights, rank = \
opt.save_dir, opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
# Directories
wdir = save_dir / 'weights'
wdir.mkdir(parents=True, exist_ok=True) # make dir
last = wdir / 'last.pt'
best = wdir / 'best.pt'
results_file = log_dir / 'results.txt'
epochs, batch_size, total_batch_size, weights, rank = \
opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
results_file = save_dir / 'results.txt'
# Save run settings
with open(log_dir / 'hyp.yaml', 'w') as f:
with open(save_dir / 'hyp.yaml', 'w') as f:
yaml.dump(hyp, f, sort_keys=False)
with open(log_dir / 'opt.yaml', 'w') as f:
with open(save_dir / 'opt.yaml', 'w') as f:
yaml.dump(vars(opt), f, sort_keys=False)
# Configure
@@ -120,8 +121,10 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
# Logging
if wandb and wandb.run is None:
id = ckpt.get('wandb_id') if 'ckpt' in locals() else None
wandb_run = wandb.init(config=opt, resume="allow", project="YOLOv5", name=log_dir.stem, id=id)
wandb_run = wandb.init(config=opt, resume="allow",
project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem,
name=save_dir.stem,
id=ckpt.get('wandb_id') if 'ckpt' in locals() else None)
# Resume
start_epoch, best_fitness = 0, 0.0
@@ -188,7 +191,7 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
c = torch.tensor(labels[:, 0]) # classes
# cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
# model._initialize_biases(cf.to(device))
plot_labels(labels, save_dir=log_dir)
plot_labels(labels, save_dir=save_dir)
if tb_writer:
# tb_writer.add_hparams(hyp, {}) # causes duplicate https://github.com/ultralytics/yolov5/pull/384
tb_writer.add_histogram('classes', c, 0)
@@ -215,7 +218,7 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
scaler = amp.GradScaler(enabled=cuda)
logger.info('Image sizes %g train, %g test\n'
'Using %g dataloader workers\nLogging results to %s\n'
'Starting training for %g epochs...' % (imgsz, imgsz_test, dataloader.num_workers, log_dir, epochs))
'Starting training for %g epochs...' % (imgsz, imgsz_test, dataloader.num_workers, save_dir, epochs))
for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------
model.train()
@@ -296,7 +299,7 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
# Plot
if ni < 3:
f = str(log_dir / f'train_batch{ni}.jpg') # filename
f = str(save_dir / f'train_batch{ni}.jpg') # filename
result = plot_images(images=imgs, targets=targets, paths=paths, fname=f)
# if tb_writer and result is not None:
# tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
@@ -321,7 +324,7 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
model=ema.ema,
single_cls=opt.single_cls,
dataloader=testloader,
save_dir=log_dir,
save_dir=save_dir,
plots=epoch == 0 or final_epoch, # plot first and last
log_imgs=opt.log_imgs if wandb else 0)
@@ -369,7 +372,7 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
if rank in [-1, 0]:
# Strip optimizers
n = opt.name if opt.name.isnumeric() else ''
fresults, flast, fbest = log_dir / f'results{n}.txt', wdir / f'last{n}.pt', wdir / f'best{n}.pt'
fresults, flast, fbest = save_dir / f'results{n}.txt', wdir / f'last{n}.pt', wdir / f'best{n}.pt'
for f1, f2 in zip([wdir / 'last.pt', wdir / 'best.pt', results_file], [flast, fbest, fresults]):
if f1.exists():
os.rename(f1, f2) # rename
@@ -378,7 +381,7 @@ def train(hyp, opt, device, tb_writer=None, wandb=None):
os.system('gsutil cp %s gs://%s/weights' % (f2, opt.bucket)) if opt.bucket else None # upload
# Finish
if not opt.evolve:
plot_results(save_dir=log_dir) # save as results.png
plot_results(save_dir=save_dir) # save as results.png
logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
dist.destroy_process_group() if rank not in [-1, 0] else None
@@ -410,11 +413,11 @@ if __name__ == '__main__':
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
parser.add_argument('--logdir', type=str, default='runs/train', help='logging directory')
parser.add_argument('--name', default='', help='name to append to --save-dir: i.e. runs/{N} -> runs/{N}_{name}')
parser.add_argument('--log-imgs', type=int, default=10, help='number of images for W&B logging, max 100')
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
parser.add_argument('--project', default='runs/train', 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')
opt = parser.parse_args()
# Set DDP variables
@@ -428,19 +431,19 @@ if __name__ == '__main__':
# Resume
if opt.resume: # resume an interrupted run
ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
log_dir = Path(ckpt).parent.parent # runs/train/exp0
opt.save_dir = Path(ckpt).parent.parent # runs/train/exp
assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
with open(log_dir / 'opt.yaml') as f:
with open(opt.save_dir / 'opt.yaml') as f:
opt = argparse.Namespace(**yaml.load(f, Loader=yaml.FullLoader)) # replace
opt.cfg, opt.weights, opt.resume = '', ckpt, True
logger.info('Resuming training from %s' % ckpt)
else:
# opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp) # check files
assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size))) # extend to 2 sizes (train, test)
log_dir = increment_dir(Path(opt.logdir) / 'exp', opt.name) # runs/exp1
opt.name = 'evolve' if opt.evolve else opt.name
opt.save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # increment run
# DDP mode
device = select_device(opt.device, batch_size=opt.batch_size)
@@ -466,8 +469,8 @@ if __name__ == '__main__':
tb_writer, wandb = None, None # init loggers
if opt.global_rank in [-1, 0]:
# Tensorboard
logger.info(f'Start Tensorboard with "tensorboard --logdir {opt.logdir}", view at http://localhost:6006/')
tb_writer = SummaryWriter(log_dir=log_dir) # runs/train/exp0
logger.info(f'Start Tensorboard with "tensorboard --logdir {opt.project}", view at http://localhost:6006/')
tb_writer = SummaryWriter(opt.save_dir) # runs/train/exp
# W&B
try:
@@ -514,7 +517,7 @@ if __name__ == '__main__':
assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
opt.notest, opt.nosave = True, True # only test/save final epoch
# ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices
yaml_file = Path(opt.logdir) / 'evolve' / 'hyp_evolved.yaml' # save best result here
yaml_file = opt.save_dir / 'hyp_evolved.yaml' # save best result here
if opt.bucket:
os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket) # download evolve.txt if exists