Skip to content

Improved detect.py timing #4741

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Sep 10, 2021
Merged

Improved detect.py timing #4741

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
51c6088
Improved detect.py timing
glenn-jocher Sep 10, 2021
9beacac
Eliminate 1 time_sync() call
glenn-jocher Sep 10, 2021
3b45a1d
Inference-only time
glenn-jocher Sep 10, 2021
2a6350b
dash
glenn-jocher Sep 10, 2021
f44a6e4
#Save section
glenn-jocher Sep 10, 2021
206af8d
Cleanup
glenn-jocher Sep 10, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 14 additions & 10 deletions detect.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@

import argparse
import sys
import time
from pathlib import Path

import cv2
Expand Down Expand Up @@ -123,8 +122,9 @@ def wrap_frozen_graph(gd, inputs, outputs):
# Run inference
if pt and device.type != 'cpu':
model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
dt, seen = [0.0, 0.0, 0.0], 0
for path, img, im0s, vid_cap in dataset:
t1 = time_sync()
if onnx:
img = img.astype('float32')
else:
Expand All @@ -133,9 +133,10 @@ def wrap_frozen_graph(gd, inputs, outputs):
img = img / 255.0 # 0 - 255 to 0.0 - 1.0
if len(img.shape) == 3:
img = img[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1

# Inference
t1 = time_sync()
if pt:
visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(img, augment=augment, visualize=visualize)[0]
Expand All @@ -162,17 +163,20 @@ def wrap_frozen_graph(gd, inputs, outputs):
pred[..., 2] *= imgsz[1] # w
pred[..., 3] *= imgsz[0] # h
pred = torch.tensor(pred)
t3 = time_sync()
dt[1] += t3 - t2

# NMS
pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
t2 = time_sync()
dt[2] += time_sync() - t3

# Second-stage classifier (optional)
if classify:
pred = apply_classifier(pred, modelc, img, im0s)

# Process predictions
for i, det in enumerate(pred): # detections per image
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
else:
Expand Down Expand Up @@ -209,8 +213,8 @@ def wrap_frozen_graph(gd, inputs, outputs):
if save_crop:
save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)

# Print time (inference + NMS)
print(f'{s}Done. ({t2 - t1:.3f}s)')
# Print time (inference-only)
print(f'{s}Done. ({t3 - t2:.3f}s)')

# Stream results
im0 = annotator.result()
Expand All @@ -237,15 +241,15 @@ def wrap_frozen_graph(gd, inputs, outputs):
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)

# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
print(f"Results saved to {colorstr('bold', save_dir)}{s}")

if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)

print(f'Done. ({time.time() - t0:.3f}s)')


def parse_opt():
parser = argparse.ArgumentParser()
Expand Down
16 changes: 8 additions & 8 deletions val.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,22 +154,22 @@ def run(data,
names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
class_map = coco80_to_coco91_class() if is_coco else list(range(1000))
s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', '[email protected]', '[email protected]:.95')
p, r, f1, mp, mr, map50, map, t0, t1, t2 = 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.
dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
loss = torch.zeros(3, device=device)
jdict, stats, ap, ap_class = [], [], [], []
for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
t_ = time_sync()
t1 = time_sync()
img = img.to(device, non_blocking=True)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
targets = targets.to(device)
nb, _, height, width = img.shape # batch size, channels, height, width
t = time_sync()
t0 += t - t_
t2 = time_sync()
dt[0] += t2 - t1

# Run model
out, train_out = model(img, augment=augment) # inference and training outputs
t1 += time_sync() - t
dt[1] += time_sync() - t2

# Compute loss
if compute_loss:
Expand All @@ -178,9 +178,9 @@ def run(data,
# Run NMS
targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device) # to pixels
lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling
t = time_sync()
t3 = time_sync()
out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
t2 += time_sync() - t
dt[2] += time_sync() - t3

# Statistics per image
for si, pred in enumerate(out):
Expand Down Expand Up @@ -247,7 +247,7 @@ def run(data,
print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))

# Print speeds
t = tuple(x / seen * 1E3 for x in (t0, t1, t2)) # speeds per image
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
if not training:
shape = (batch_size, 3, imgsz, imgsz)
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)
Expand Down