def check_anchors(dataset, model, thr=4.0, imgsz=640):
# Check anchor fit to data, recompute if necessary
m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh
def metric(k): # compute metric
r = wh[:, None] / k[None]
x = torch.min(r, 1 / r).min(2)[0] # ratio metric
best = x.max(1)[0] # best_x
aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold
bpr = (best > 1 / thr).float().mean() # best possible recall
return bpr, aat
anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors
bpr, aat = metric(anchors.cpu().view(-1, 2))
s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). '
if bpr > 0.98: # threshold to recompute
LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset тЬЕ'))
else:
LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset тЪая╕П, attempting to improve...'))
na = m.anchors.numel() // 2 # number of anchors
try:
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
except Exception as e:
LOGGER.info(f'{PREFIX}ERROR: {e}')
new_bpr = metric(anchors)[0]
if new_bpr > bpr: # replace anchors
anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
check_anchor_order(m)
LOGGER.info(f'{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
else:
LOGGER.info(f'{PREFIX}Original anchors better than new anchors. Proceeding with original anchors.')
def start(self):
self.csv = True # always log to csv
# Message
try:
import wandb
except ImportError:
prefix = colorstr('Weights & Biases: ')
s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)"
print(emojis(s))
# TensorBoard
s = self.save_dir
if 'tb' in self.include and not self.opt.evolve:
prefix = colorstr('TensorBoard: ')
self.logger.info(
f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/"
)
self.tb = SummaryWriter(str(s))
# W&B
try:
assert 'wandb' in self.include and wandb
run_id = torch.load(
self.weights).get('wandb_id') if self.opt.resume else None
self.opt.hyp = self.hyp # add hyperparameters
self.wandb = WandbLogger(self.opt, run_id, self.data_dict)
except:
self.wandb = None
return self
def start(self):
self.csv = True # always log to csv
# Message
if not wandb:
prefix = colorstr('Weights & Biases: ')
s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)"
print(emojis(s))
# TensorBoard
s = self.save_dir
if 'tb' in self.include and not self.opt.evolve:
prefix = colorstr('TensorBoard: ')
self.logger.info(
f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/"
)
self.tb = SummaryWriter(str(s))
# W&B
if wandb and 'wandb' in self.include:
wandb_artifact_resume = isinstance(
self.opt.resume,
str) and self.opt.resume.startswith('wandb-artifact://')
run_id = torch.load(self.weights).get(
'wandb_id'
) if self.opt.resume and not wandb_artifact_resume else None
self.opt.hyp = self.hyp # add hyperparameters
self.wandb = WandbLogger(self.opt, run_id)
else:
self.wandb = None
return self
def main(opt):
check_requirements(requirements=ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
if opt.task in ('train', 'val', 'test'): # run normally
if opt.conf_thres > 0.001: # https://github.com/ultralytics/yolov5/issues/1466
LOGGER.info(emojis(f'WARNING: confidence threshold {opt.conf_thres} > 0.001 produces invalid results тЪая╕П'))
run(**vars(opt))
else:
weights = opt.weights if isinstance(opt.weights, list) else [opt.weights]
opt.half = True # FP16 for fastest results
if opt.task == 'speed': # speed benchmarks
# python val.py --task speed --data coco.yaml --batch 1 --weights yolov5n.pt yolov5s.pt...
opt.conf_thres, opt.iou_thres, opt.save_json = 0.25, 0.45, False
for opt.weights in weights:
run(**vars(opt), plots=False)
elif opt.task == 'study': # speed vs mAP benchmarks
# python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n.pt yolov5s.pt...
for opt.weights in weights:
f = f'study_{Path(opt.data).stem}_{Path(opt.weights).stem}.txt' # filename to save to
x, y = list(range(256, 1536 + 128, 128)), [] # x axis (image sizes), y axis
for opt.imgsz in x: # img-size
LOGGER.info(f'\nRunning {f} --imgsz {opt.imgsz}...')
r, _, t = run(**vars(opt), plots=False)
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
plot_val_study(x=x) # plot
def notebook_init(verbose=True):
# Check system software and hardware
print('Checking setup...')
import os
import shutil
from utils.general import check_requirements, emojis, is_colab
from utils.torch_utils import select_device # imports
check_requirements(('psutil', 'IPython'))
import psutil
from IPython import display # to display images and clear console output
if is_colab():
shutil.rmtree(
'/content/sample_data',
ignore_errors=True) # remove colab /sample_data directory
if verbose:
# System info
# gb = 1 / 1000 ** 3 # bytes to GB
gib = 1 / 1024**3 # bytes to GiB
ram = psutil.virtual_memory().total
total, used, free = shutil.disk_usage("/")
display.clear_output()
s = f'({os.cpu_count()} CPUs, {ram * gib:.1f} GB RAM, {(total - free) * gib:.1f}/{total * gib:.1f} GB disk)'
else:
s = ''
select_device(newline=False)
print(emojis(f'Setup complete ✅ {s}'))
return display
def __init__(self,
save_dir=None,
weights=None,
opt=None,
hyp=None,
logger=None,
include=LOGGERS):
self.save_dir = save_dir
self.weights = weights
self.opt = opt
self.hyp = hyp
self.logger = logger # for printing results to console
self.include = include
self.keys = [
'train/box_loss',
'train/obj_loss',
'train/cls_loss', # train loss
'metrics/precision',
'metrics/recall',
'metrics/mAP_0.5',
'metrics/mAP_0.5:0.95', # metrics
'val/box_loss',
'val/obj_loss',
'val/cls_loss', # val loss
'x/lr0',
'x/lr1',
'x/lr2'
] # params
for k in LOGGERS:
setattr(self, k, None) # init empty logger dictionary
self.csv = True # always log to csv
# Message
if not wandb:
prefix = colorstr('Weights & Biases: ')
s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs (RECOMMENDED)"
print(emojis(s))
# TensorBoard
s = self.save_dir
if 'tb' in self.include and not self.opt.evolve:
prefix = colorstr('TensorBoard: ')
self.logger.info(
f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/"
)
self.tb = SummaryWriter(str(s))
# W&B
if wandb and 'wandb' in self.include:
wandb_artifact_resume = isinstance(
self.opt.resume,
str) and self.opt.resume.startswith('wandb-artifact://')
run_id = torch.load(self.weights).get(
'wandb_id'
) if self.opt.resume and not wandb_artifact_resume else None
self.opt.hyp = self.hyp # add hyperparameters
self.wandb = WandbLogger(self.opt, run_id)
else:
self.wandb = None
def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
# Automatically estimate best batch size to use `fraction` of available CUDA memory
# Usage:
# import torch
# from utils.autobatch import autobatch
# model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)
# print(autobatch(model))
# Check device
prefix = colorstr('AutoBatch: ')
LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}')
device = next(model.parameters()).device # get model device
if device.type == 'cpu':
LOGGER.info(
f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}'
)
return batch_size
# Inspect CUDA memory
gb = 1 << 30 # bytes to GiB (1024 ** 3)
d = str(device).upper() # 'CUDA:0'
properties = torch.cuda.get_device_properties(device) # device properties
t = properties.total_memory / gb # GiB total
r = torch.cuda.memory_reserved(device) / gb # GiB reserved
a = torch.cuda.memory_allocated(device) / gb # GiB allocated
f = t - (r + a) # GiB free
LOGGER.info(
f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free'
)
# Profile batch sizes
batch_sizes = [1, 2, 4, 8, 16]
try:
img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
results = profile(img, model, n=3, device=device)
except Exception as e:
LOGGER.warning(f'{prefix}{e}')
# Fit a solution
y = [x[2] for x in results if x] # memory [2]
p = np.polyfit(batch_sizes[:len(y)], y,
deg=1) # first degree polynomial fit
b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size)
if None in results: # some sizes failed
i = results.index(None) # first fail index
if b >= batch_sizes[i]: # y intercept above failure point
b = batch_sizes[max(i - 1, 0)] # select prior safe point
fraction = np.polyval(p, b) / t # actual fraction predicted
LOGGER.info(
emojis(
f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅'
))
return b
def notebook_init():
# For YOLOv5 notebooks
print('Checking setup...')
from IPython import display # to display images and clear console output
from utils.general import emojis
from utils.torch_utils import select_device # YOLOv5 imports
display.clear_output()
select_device(newline=False)
print(emojis('Setup complete ✅'))
return display
