Improved Profile() inference timing (#9024)
* Improved `Profile()` class * Update predict.py * Update val.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update val.py * Update AutoShape Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Glenn Jocherandpre-commit-ci[bot] authored and GitHub committed
1 parent
c0e7a776cd
commit
d40cd0d454
6 files changed
+132
-133
No files matched your search
+58
-57
@@ -21,10 +21,11 @@ from PIL import Image
|
||||
from torch.cuda import amp
|
||||
|
||||
from utils.dataloaders import exif_transpose, letterbox
|
||||
from utils.general import (LOGGER, ROOT, check_requirements, check_suffix, check_version, colorstr, increment_path,
|
||||
make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh, yaml_load)
|
||||
from utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr,
|
||||
increment_path, make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh,
|
||||
yaml_load)
|
||||
from utils.plots import Annotator, colors, save_one_box
|
||||
from utils.torch_utils import copy_attr, smart_inference_mode, time_sync
|
||||
from utils.torch_utils import copy_attr, smart_inference_mode
|
||||
|
||||
|
||||
def autopad(k, p=None): # kernel, padding
|
||||
@@ -587,9 +588,9 @@ class AutoShape(nn.Module):
|
||||
return self
|
||||
|
||||
@smart_inference_mode()
|
||||
def forward(self, imgs, size=640, augment=False, profile=False):
|
||||
def forward(self, ims, size=640, augment=False, profile=False):
|
||||
# Inference from various sources. For height=640, width=1280, RGB images example inputs are:
|
||||
# file: imgs = 'data/images/zidane.jpg' # str or PosixPath
|
||||
# file: ims = 'data/images/zidane.jpg' # str or PosixPath
|
||||
# URI: = 'https://ultralytics.com/images/zidane.jpg'
|
||||
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
|
||||
# PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
|
||||
@@ -597,65 +598,65 @@ class AutoShape(nn.Module):
|
||||
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
|
||||
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
|
||||
|
||||
t = [time_sync()]
|
||||
p = next(self.model.parameters()) if self.pt else torch.zeros(1, device=self.model.device) # for device, type
|
||||
autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference
|
||||
if isinstance(imgs, torch.Tensor): # torch
|
||||
with amp.autocast(autocast):
|
||||
return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
|
||||
dt = (Profile(), Profile(), Profile())
|
||||
with dt[0]:
|
||||
p = next(self.model.parameters()) if self.pt else torch.zeros(1, device=self.model.device) # param
|
||||
autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference
|
||||
if isinstance(ims, torch.Tensor): # torch
|
||||
with amp.autocast(autocast):
|
||||
return self.model(ims.to(p.device).type_as(p), augment, profile) # inference
|
||||
|
||||
# Pre-process
|
||||
n, imgs = (len(imgs), list(imgs)) if isinstance(imgs, (list, tuple)) else (1, [imgs]) # number, list of images
|
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
|
||||
for i, im in enumerate(imgs):
|
||||
f = f'image{i}' # filename
|
||||
if isinstance(im, (str, Path)): # filename or uri
|
||||
im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
|
||||
im = np.asarray(exif_transpose(im))
|
||||
elif isinstance(im, Image.Image): # PIL Image
|
||||
im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
|
||||
files.append(Path(f).with_suffix('.jpg').name)
|
||||
if im.shape[0] < 5: # image in CHW
|
||||
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
|
||||
im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR) # enforce 3ch input
|
||||
s = im.shape[:2] # HWC
|
||||
shape0.append(s) # image shape
|
||||
g = (size / max(s)) # gain
|
||||
shape1.append([y * g for y in s])
|
||||
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
|
||||
shape1 = [make_divisible(x, self.stride) if self.pt else size for x in np.array(shape1).max(0)] # inf shape
|
||||
x = [letterbox(im, shape1, auto=False)[0] for im in imgs] # pad
|
||||
x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2))) # stack and BHWC to BCHW
|
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32
|
||||
t.append(time_sync())
|
||||
# Pre-process
|
||||
n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims]) # number, list of images
|
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
|
||||
for i, im in enumerate(ims):
|
||||
f = f'image{i}' # filename
|
||||
if isinstance(im, (str, Path)): # filename or uri
|
||||
im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
|
||||
im = np.asarray(exif_transpose(im))
|
||||
elif isinstance(im, Image.Image): # PIL Image
|
||||
im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
|
||||
files.append(Path(f).with_suffix('.jpg').name)
|
||||
if im.shape[0] < 5: # image in CHW
|
||||
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
|
||||
im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR) # enforce 3ch input
|
||||
s = im.shape[:2] # HWC
|
||||
shape0.append(s) # image shape
|
||||
g = (size / max(s)) # gain
|
||||
shape1.append([y * g for y in s])
|
||||
ims[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
|
||||
shape1 = [make_divisible(x, self.stride) if self.pt else size for x in np.array(shape1).max(0)] # inf shape
|
||||
x = [letterbox(im, shape1, auto=False)[0] for im in ims] # pad
|
||||
x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2))) # stack and BHWC to BCHW
|
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32
|
||||
|
||||
with amp.autocast(autocast):
|
||||
# Inference
|
||||
y = self.model(x, augment, profile) # forward
|
||||
t.append(time_sync())
|
||||
with dt[1]:
|
||||
y = self.model(x, augment, profile) # forward
|
||||
|
||||
# Post-process
|
||||
y = non_max_suppression(y if self.dmb else y[0],
|
||||
self.conf,
|
||||
self.iou,
|
||||
self.classes,
|
||||
self.agnostic,
|
||||
self.multi_label,
|
||||
max_det=self.max_det) # NMS
|
||||
for i in range(n):
|
||||
scale_coords(shape1, y[i][:, :4], shape0[i])
|
||||
with dt[2]:
|
||||
y = non_max_suppression(y if self.dmb else y[0],
|
||||
self.conf,
|
||||
self.iou,
|
||||
self.classes,
|
||||
self.agnostic,
|
||||
self.multi_label,
|
||||
max_det=self.max_det) # NMS
|
||||
for i in range(n):
|
||||
scale_coords(shape1, y[i][:, :4], shape0[i])
|
||||
|
||||
t.append(time_sync())
|
||||
return Detections(imgs, y, files, t, self.names, x.shape)
|
||||
return Detections(ims, y, files, dt, self.names, x.shape)
|
||||
|
||||
|
||||
class Detections:
|
||||
# YOLOv5 detections class for inference results
|
||||
def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None):
|
||||
def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None):
|
||||
super().__init__()
|
||||
d = pred[0].device # device
|
||||
gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations
|
||||
self.imgs = imgs # list of images as numpy arrays
|
||||
gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims] # normalizations
|
||||
self.ims = ims # list of images as numpy arrays
|
||||
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
|
||||
self.names = names # class names
|
||||
self.files = files # image filenames
|
||||
@@ -665,12 +666,12 @@ class Detections:
|
||||
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
|
||||
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
|
||||
self.n = len(self.pred) # number of images (batch size)
|
||||
self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
|
||||
self.t = tuple(x.t / self.n * 1E3 for x in times) # timestamps (ms)
|
||||
self.s = shape # inference BCHW shape
|
||||
|
||||
def display(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')):
|
||||
crops = []
|
||||
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
|
||||
for i, (im, pred) in enumerate(zip(self.ims, self.pred)):
|
||||
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
|
||||
if pred.shape[0]:
|
||||
for c in pred[:, -1].unique():
|
||||
@@ -705,7 +706,7 @@ class Detections:
|
||||
if i == self.n - 1:
|
||||
LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
|
||||
if render:
|
||||
self.imgs[i] = np.asarray(im)
|
||||
self.ims[i] = np.asarray(im)
|
||||
if crop:
|
||||
if save:
|
||||
LOGGER.info(f'Saved results to {save_dir}\n')
|
||||
@@ -728,7 +729,7 @@ class Detections:
|
||||
|
||||
def render(self, labels=True):
|
||||
self.display(render=True, labels=labels) # render results
|
||||
return self.imgs
|
||||
return self.ims
|
||||
|
||||
def pandas(self):
|
||||
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
|
||||
@@ -743,9 +744,9 @@ class Detections:
|
||||
def tolist(self):
|
||||
# return a list of Detections objects, i.e. 'for result in results.tolist():'
|
||||
r = range(self.n) # iterable
|
||||
x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
|
||||
x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
|
||||
# for d in x:
|
||||
# for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
|
||||
# for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
|
||||
# setattr(d, k, getattr(d, k)[0]) # pop out of list
|
||||
return x
|
||||
|
||||
|
||||
Reference in new issue
Block a user