HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.239 Ultralytics Actions and hub-sdk adoption (#7431)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 03:16:08 +01:00 • committed by GitHub
parent e795277391
commit fe27db2f6e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
139 changed files with 6870 additions and 5125 deletions
Download patch file Download diff file Expand all files Collapse all files

20
ultralytics/utils/autobatch.py
View file

@ -42,14 +42,14 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
"""
# Check device
prefix = colorstr('AutoBatch: ')
LOGGER.info(f'{prefix}Computing optimal batch size for imgsz={imgsz}')
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}')
if device.type == "cpu":
LOGGER.info(f"{prefix}CUDA not detected, using default CPU batch-size {batch_size}")
return batch_size
if torch.backends.cudnn.benchmark:
LOGGER.info(f'{prefix} ⚠️ Requires torch.backends.cudnn.benchmark=False, using default batch-size {batch_size}')
LOGGER.info(f"{prefix} ⚠️ Requires torch.backends.cudnn.benchmark=False, using default batch-size {batch_size}")
return batch_size
# Inspect CUDA memory
@ -60,7 +60,7 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
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')
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]
@ -70,7 +70,7 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
# 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
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
@ -78,11 +78,11 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch):
b = batch_sizes[max(i - 1, 0)] # select prior safe point
if b < 1 or b > 1024: # b outside of safe range
b = batch_size
LOGGER.info(f'{prefix}WARNING ⚠️ CUDA anomaly detected, using default batch-size {batch_size}.')
LOGGER.info(f"{prefix}WARNING ⚠️ CUDA anomaly detected, using default batch-size {batch_size}.")
fraction = (np.polyval(p, b) + r + a) / t # actual fraction predicted
LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅')
LOGGER.info(f"{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅")
return b
except Exception as e:
LOGGER.warning(f'{prefix}WARNING ⚠️ error detected: {e}, using default batch-size {batch_size}.')
LOGGER.warning(f"{prefix}WARNING ⚠️ error detected: {e}, using default batch-size {batch_size}.")
return batch_size