zjc
/
yolov5
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Update test.py profiling (#3555) 

* Update test.py profiling

* half_precision to half

* inplace
This commit is contained in:
Glenn Jocher 2021-06-09 16:25:17 +02:00 committed by GitHub
parent 8b5086c21b
commit 5948f20a3d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 39 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
test.py
View File

@ -38,7 +38,7 @@ def test(data,
plots=True, plots=True,
wandb_logger=None, wandb_logger=None,
compute_loss=None, compute_loss=None,
half_precision=True, half=True,
opt=None): opt=None):
# Initialize/load model and set device # Initialize/load model and set device
training = model is not None training = model is not None
@ -63,7 +63,7 @@ def test(data,
# model = nn.DataParallel(model) # model = nn.DataParallel(model)
# Half # Half
half = device.type != 'cpu' and half_precision # half precision only supported on CUDA half &= device.type != 'cpu' # half precision only supported on CUDA
if half: if half:
model.half() model.half()
@ -95,20 +95,22 @@ def test(data,
names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)} names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
coco91class = coco80_to_coco91_class() coco91class = coco80_to_coco91_class()
s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95') s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0. p, r, f1, mp, mr, map50, map, t0, t1, t2 = 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.
loss = torch.zeros(3, device=device) loss = torch.zeros(3, device=device)
jdict, stats, ap, ap_class, wandb_images = [], [], [], [], [] jdict, stats, ap, ap_class, wandb_images = [], [], [], [], []
for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)): for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
t_ = time_synchronized()
img = img.to(device, non_blocking=True) img = img.to(device, non_blocking=True)
img = img.half() if half else img.float() # uint8 to fp16/32 img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0 img /= 255.0 # 0 - 255 to 0.0 - 1.0
targets = targets.to(device) targets = targets.to(device)
nb, _, height, width = img.shape # batch size, channels, height, width nb, _, height, width = img.shape # batch size, channels, height, width
t = time_synchronized()
t0 += t - t_
# Run model # Run model
t = time_synchronized()
out, train_out = model(img, augment=augment) # inference and training outputs out, train_out = model(img, augment=augment) # inference and training outputs
t0 += time_synchronized() - t t1 += time_synchronized() - t
# Compute loss # Compute loss
if compute_loss: if compute_loss:
@ -119,7 +121,7 @@ def test(data,
lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else [] # for autolabelling
t = time_synchronized() t = time_synchronized()
out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls) out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
t1 += time_synchronized() - t t2 += time_synchronized() - t
# Statistics per image # Statistics per image
for si, pred in enumerate(out): for si, pred in enumerate(out):
@ -236,9 +238,10 @@ def test(data,
print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i])) print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
# Print speeds # Print speeds
t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size) # tuple t = tuple(x / seen * 1E3 for x in (t0, t1, t2)) # speeds per image
if not training: if not training:
print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t) shape = (batch_size, 3, imgsz, imgsz)
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {shape}' % t)
# Plots # Plots
if plots: if plots:
@ -327,24 +330,25 @@ if __name__ == '__main__':
save_txt=opt.save_txt | opt.save_hybrid, save_txt=opt.save_txt | opt.save_hybrid,
save_hybrid=opt.save_hybrid, save_hybrid=opt.save_hybrid,
save_conf=opt.save_conf, save_conf=opt.save_conf,
half_precision=opt.half, half=opt.half,
opt=opt opt=opt
) )
elif opt.task == 'speed': # speed benchmarks elif opt.task == 'speed': # speed benchmarks
for w in opt.weights: for w in opt.weights if isinstance(opt.weights, list) else [opt.weights]:
test(opt.data, w, opt.batch_size, opt.img_size, 0.25, 0.45, save_json=False, plots=False, opt=opt) test(opt.data, w, opt.batch_size, opt.img_size, 0.25, 0.45, save_json=False, plots=False, half=True,
opt=opt)
elif opt.task == 'study': # run over a range of settings and save/plot elif opt.task == 'study': # run over a range of settings and save/plot
# python test.py --task study --data coco.yaml --iou 0.7 --weights yolov5s.pt yolov5m.pt yolov5l.pt yolov5x.pt # python test.py --task study --data coco.yaml --iou 0.7 --weights yolov5s.pt yolov5m.pt yolov5l.pt yolov5x.pt
x = list(range(256, 1536 + 128, 128)) # x axis (image sizes) x = list(range(256, 1536 + 128, 128)) # x axis (image sizes)
for w in opt.weights: for w in opt.weights if isinstance(opt.weights, list) else [opt.weights]:
f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt' # filename to save to f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt' # filename to save to
y = [] # y axis y = [] # y axis
for i in x: # img-size for i in x: # img-size
print(f'\nRunning {f} point {i}...') print(f'\nRunning {f} point {i}...')
r, _, t = test(opt.data, w, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json, r, _, t = test(opt.data, w, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json,
plots=False, opt=opt) plots=False, half=True, opt=opt)
y.append(r + t) # results and times y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt') os.system('zip -r study.zip study_*.txt')

4
train.py
View File

@ -74,7 +74,7 @@ def train(hyp, opt, device, tb_writer=None):
loggers['wandb'] = wandb_logger.wandb loggers['wandb'] = wandb_logger.wandb
data_dict = wandb_logger.data_dict data_dict = wandb_logger.data_dict
if wandb_logger.wandb: if wandb_logger.wandb:
weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp # WandbLogger might update weights, epochs if resuming weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp # may update weights, epochs if resuming
nc = 1 if single_cls else int(data_dict['nc']) # number of classes nc = 1 if single_cls else int(data_dict['nc']) # number of classes
names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names
@ -354,7 +354,7 @@ def train(hyp, opt, device, tb_writer=None):
final_epoch = epoch + 1 == epochs final_epoch = epoch + 1 == epochs
if not opt.notest or final_epoch: # Calculate mAP if not opt.notest or final_epoch: # Calculate mAP
wandb_logger.current_epoch = epoch + 1 wandb_logger.current_epoch = epoch + 1
results, maps, times = test.test(data_dict, results, maps, _ = test.test(data_dict,
batch_size=batch_size * 2, batch_size=batch_size * 2,
imgsz=imgsz_test, imgsz=imgsz_test,
model=ema.ema, model=ema.ema,

17
utils/plots.py
View File

@ -3,7 +3,6 @@
import glob import glob
import math import math
import os import os
import random
from copy import copy from copy import copy
from pathlib import Path from pathlib import Path
@ -252,21 +251,23 @@ def plot_targets_txt(): # from utils.plots import *; plot_targets_txt()
def plot_study_txt(path='', x=None): # from utils.plots import *; plot_study_txt() def plot_study_txt(path='', x=None): # from utils.plots import *; plot_study_txt()
# Plot study.txt generated by test.py # Plot study.txt generated by test.py
fig, ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True) plot2 = False # plot additional results
# ax = ax.ravel() if plot2:
ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)[1].ravel()
fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True) fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
# for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]: # for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]:
for f in sorted(Path(path).glob('study*.txt')): for f in sorted(Path(path).glob('study*.txt')):
y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
x = np.arange(y.shape[1]) if x is None else np.array(x) x = np.arange(y.shape[1]) if x is None else np.array(x)
s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_inference (ms/img)', 't_NMS (ms/img)', 't_total (ms/img)'] if plot2:
# for i in range(7): s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_preprocess (ms/img)', 't_inference (ms/img)', 't_NMS (ms/img)']
# ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8) for i in range(7):
# ax[i].set_title(s[i]) ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8)
ax[i].set_title(s[i])
j = y[3].argmax() + 1 j = y[3].argmax() + 1
ax2.plot(y[6, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8, ax2.plot(y[5, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8,
label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO')) label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5], ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],