mirrors
/
yolov5
mirror of https://github.com/ultralytics/yolov5.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Increment train, test, detect runs/ (#1322) 

* Increment train, test, detect runs/

* Update ci-testing.yml

* inference/images to data/images

* move images

* runs/exp to runs/train/exp

* update 'results saved to %s' str
pull/1323/head
Glenn Jocher 2020-11-08 19:39:05 +01:00 committed by GitHub
parent d3e7778151
commit 4821d076e2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
13 changed files with 76 additions and 382 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/ci-testing.yml vendored
View File

@ -66,10 +66,10 @@ jobs:
python train.py --img 256 --batch 8 --weights weights/${{ matrix.model }}.pt --cfg models/${{ matrix.model }}.yaml --epochs 1 --device $di
# detect
python detect.py --weights weights/${{ matrix.model }}.pt --device $di
python detect.py --weights runs/exp0/weights/last.pt --device $di
python detect.py --weights runs/train/exp0/weights/last.pt --device $di
# test
python test.py --img 256 --batch 8 --weights weights/${{ matrix.model }}.pt --device $di
python test.py --img 256 --batch 8 --weights runs/exp0/weights/last.pt --device $di
python test.py --img 256 --batch 8 --weights runs/train/exp0/weights/last.pt --device $di
python models/yolo.py --cfg models/${{ matrix.model }}.yaml # inspect
python models/export.py --img 256 --batch 1 --weights weights/${{ matrix.model }}.pt # export

4
.gitignore vendored
View File

@ -26,8 +26,8 @@
storage.googleapis.com
runs/*
data/*
!data/samples/zidane.jpg
!data/samples/bus.jpg
!data/images/zidane.jpg
!data/images/bus.jpg
!data/coco.names
!data/coco_paper.names
!data/coco.data

2
Dockerfile
View File

@ -46,7 +46,7 @@ COPY . /usr/src/app
# sudo docker commit 092b16b25c5b usr/resume && sudo docker run -it --gpus all --ipc=host -v "$(pwd)"/coco:/usr/src/coco --entrypoint=sh usr/resume
# Send weights to GCP
# python -c "from utils.general import *; strip_optimizer('runs/exp0_*/weights/best.pt', 'tmp.pt')" && gsutil cp tmp.pt gs://*.pt
# python -c "from utils.general import *; strip_optimizer('runs/train/exp0_*/weights/best.pt', 'tmp.pt')" && gsutil cp tmp.pt gs://*.pt
# Clean up
# docker system prune -a --volumes

14
README.md
View File

@ -70,7 +70,7 @@ YOLOv5 may be run in any of the following up-to-date verified environments (with
## Inference
detect.py runs inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases) and saving results to `inference/output`.
detect.py runs inference on a variety of sources, downloading models automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`.
```bash
$ python detect.py --source 0 # webcam
file.jpg # image
@ -82,20 +82,20 @@ $ python detect.py --source 0 # webcam
http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8 # http stream
```
To run inference on example images in `inference/images`:
To run inference on example images in `data/images`:
```bash
$ python detect.py --source inference/images --weights yolov5s.pt --conf 0.25
$ python detect.py --source data/images --weights yolov5s.pt --conf 0.25
Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', img_size=640, iou_thres=0.45, output='inference/output', save_conf=False, save_txt=False, source='inference/images', update=False, view_img=False, weights='yolov5s.pt')
Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', img_size=640, iou_thres=0.45, output='runs/detect', save_conf=False, save_txt=False, source='data/images', update=False, view_img=False, weights='yolov5s.pt')
Using CUDA device0 _CudaDeviceProperties(name='Tesla V100-SXM2-16GB', total_memory=16160MB)
Downloading https://github.com/ultralytics/yolov5/releases/download/v3.0/yolov5s.pt to yolov5s.pt... 100%|██████████████| 14.5M/14.5M [00:00<00:00, 21.3MB/s]
Fusing layers...
Model Summary: 140 layers, 7.45958e+06 parameters, 0 gradients
image 1/2 yolov5/inference/images/bus.jpg: 640x480 4 persons, 1 buss, 1 skateboards, Done. (0.013s)
image 2/2 yolov5/inference/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.013s)
Results saved to yolov5/inference/output
image 1/2 data/images/bus.jpg: 640x480 4 persons, 1 buss, 1 skateboards, Done. (0.013s)
image 2/2 data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.013s)
Results saved to runs/detect/exp0
Done. (0.124s)
```
<img src="https://user-images.githubusercontent.com/26833433/97107365-685a8d80-16c7-11eb-8c2e-83aac701d8b9.jpeg" width="500">

0
inference/images/bus.jpg → data/images/bus.jpg
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 476 KiB

After

Width:  |  Height:  |  Size: 476 KiB

0
inference/images/zidane.jpg → data/images/zidane.jpg
View File

Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 165 KiB

After

Width:  |  Height:  |  Size: 165 KiB

38
detect.py
View File

@ -1,6 +1,5 @@
import argparse
import os
import shutil
import time
from pathlib import Path
@ -11,23 +10,25 @@ from numpy import random
from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import (
check_img_size, non_max_suppression, apply_classifier, scale_coords,
xyxy2xywh, plot_one_box, strip_optimizer, set_logging)
from utils.general import check_img_size, non_max_suppression, apply_classifier, scale_coords, xyxy2xywh, \
plot_one_box, strip_optimizer, set_logging, increment_dir
from utils.torch_utils import select_device, load_classifier, time_synchronized
def detect(save_img=False):
out, source, weights, view_img, save_txt, imgsz = \
opt.save_dir, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
save_dir, source, weights, view_img, save_txt, imgsz = \
Path(opt.save_dir), opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
webcam = source.isnumeric() or source.startswith(('rtsp://', 'rtmp://', 'http://')) or source.endswith('.txt')
# Directories
if save_dir == Path('runs/detect'): # if default
os.makedirs('runs/detect', exist_ok=True) # make base
save_dir = Path(increment_dir(save_dir / 'exp', opt.name)) # increment run
os.makedirs(save_dir / 'labels' if save_txt else save_dir, exist_ok=True) # make new dir
# Initialize
set_logging()
device = select_device(opt.device)
if os.path.exists(out): # output dir
shutil.rmtree(out) # delete dir
os.makedirs(out) # make new dir
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
@ -83,12 +84,12 @@ def detect(save_img=False):
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
p, s, im0 = Path(path[i]), '%g: ' % i, im0s[i].copy()
else:
p, s, im0 = path, '', im0s
p, s, im0 = Path(path), '', im0s
save_path = str(Path(out) / Path(p).name)
txt_path = str(Path(out) / Path(p).stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '')
save_path = str(save_dir / p.name)
txt_path = str(save_dir / 'labels' / p.stem) + ('_%g' % dataset.frame if dataset.mode == 'video' else '')
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
if det is not None and len(det):
@ -104,7 +105,7 @@ def detect(save_img=False):
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, conf, *xywh) if opt.save_conf else (cls, *xywh) # label format
line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line) + '\n') % line)
@ -139,7 +140,7 @@ def detect(save_img=False):
vid_writer.write(im0)
if save_txt or save_img:
print('Results saved to %s' % Path(out))
print('Results saved to %s' % save_dir)
print('Done. (%.3fs)' % (time.time() - t0))
@ -147,15 +148,16 @@ def detect(save_img=False):
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--source', type=str, default='inference/images', help='source') # file/folder, 0 for webcam
parser.add_argument('--source', type=str, default='data/images', help='source') # file/folder, 0 for webcam
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true', help='display results')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-txt', action='store_false', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-dir', type=str, default='inference/output', help='directory to save results')
parser.add_argument('--save-dir', type=str, default='runs/detect', help='directory to save results')
parser.add_argument('--name', default='', help='name to append to --save-dir: i.e. runs/{N} -> runs/{N}_{name}')
parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true', help='augmented inference')

2
hubconf.py
View File

@ -113,6 +113,6 @@ if __name__ == '__main__':
# Verify inference
from PIL import Image
img = Image.open('inference/images/zidane.jpg')
img = Image.open('data/images/zidane.jpg')
y = model(img)
print(y[0].shape)

307
sotabench.py
View File

@ -1,307 +0,0 @@
import argparse
import glob
import os
import shutil
from pathlib import Path
import numpy as np
import torch
import yaml
from sotabencheval.object_detection import COCOEvaluator
from sotabencheval.utils import is_server
from tqdm import tqdm
from models.experimental import attempt_load
from utils.datasets import create_dataloader
from utils.general import (
coco80_to_coco91_class, check_dataset, check_file, check_img_size, compute_loss, non_max_suppression, scale_coords,
xyxy2xywh, clip_coords, set_logging)
from utils.torch_utils import select_device, time_synchronized
DATA_ROOT = './.data/vision/coco' if is_server() else '../coco' # sotabench data dir
def test(data,
weights=None,
batch_size=16,
imgsz=640,
conf_thres=0.001,
iou_thres=0.6, # for NMS
save_json=False,
single_cls=False,
augment=False,
verbose=False,
model=None,
dataloader=None,
save_dir='',
merge=False,
save_txt=False):
# Initialize/load model and set device
training = model is not None
if training: # called by train.py
device = next(model.parameters()).device # get model device
else: # called directly
set_logging()
device = select_device(opt.device, batch_size=batch_size)
merge, save_txt = opt.merge, opt.save_txt # use Merge NMS, save *.txt labels
if save_txt:
out = Path('inference/output')
if os.path.exists(out):
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
# Remove previous
for f in glob.glob(str(Path(save_dir) / 'test_batch*.jpg')):
os.remove(f)
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model
imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size
# Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99
# if device.type != 'cpu' and torch.cuda.device_count() > 1:
# model = nn.DataParallel(model)
# Half
half = device.type != 'cpu' # half precision only supported on CUDA
if half:
model.half()
# Configure
model.eval()
with open(data) as f:
data = yaml.load(f, Loader=yaml.FullLoader) # model dict
check_dataset(data) # check
nc = 1 if single_cls else int(data['nc']) # number of classes
iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for mAP@0.5:0.95
niou = iouv.numel()
# Dataloader
if not training:
img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
_ = model(img.half() if half else img) if device.type != 'cpu' else None # run once
path = data['test'] if opt.task == 'test' else data['val'] # path to val/test images
dataloader = create_dataloader(path, imgsz, batch_size, model.stride.max(), opt,
hyp=None, augment=False, cache=True, pad=0.5, rect=True)[0]
seen = 0
names = model.names if hasattr(model, 'names') else model.module.names
coco91class = coco80_to_coco91_class()
s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Targets', '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.
loss = torch.zeros(3, device=device)
jdict, stats, ap, ap_class = [], [], [], []
evaluator = COCOEvaluator(root=DATA_ROOT, model_name=opt.weights.replace('.pt', ''))
for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
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
whwh = torch.Tensor([width, height, width, height]).to(device)
# Disable gradients
with torch.no_grad():
# Run model
t = time_synchronized()
inf_out, train_out = model(img, augment=augment) # inference and training outputs
t0 += time_synchronized() - t
# Compute loss
if training: # if model has loss hyperparameters
loss += compute_loss([x.float() for x in train_out], targets, model)[1][:3] # box, obj, cls
# Run NMS
t = time_synchronized()
output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres, merge=merge)
t1 += time_synchronized() - t
# Statistics per image
for si, pred in enumerate(output):
labels = targets[targets[:, 0] == si, 1:]
nl = len(labels)
tcls = labels[:, 0].tolist() if nl else [] # target class
seen += 1
if pred is None:
if nl:
stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
continue
# Append to text file
if save_txt:
gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]] # normalization gain whwh
x = pred.clone()
x[:, :4] = scale_coords(img[si].shape[1:], x[:, :4], shapes[si][0], shapes[si][1]) # to original
for *xyxy, conf, cls in x:
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
with open(str(out / Path(paths[si]).stem) + '.txt', 'a') as f:
f.write(('%g ' * 5 + '\n') % (cls, *xywh)) # label format
# Clip boxes to image bounds
clip_coords(pred, (height, width))
# Append to pycocotools JSON dictionary
if save_json:
# [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
image_id = Path(paths[si]).stem
box = pred[:, :4].clone() # xyxy
scale_coords(img[si].shape[1:], box, shapes[si][0], shapes[si][1]) # to original shape
box = xyxy2xywh(box) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for p, b in zip(pred.tolist(), box.tolist()):
result = {'image_id': int(image_id) if image_id.isnumeric() else image_id,
'category_id': coco91class[int(p[5])],
'bbox': [round(x, 3) for x in b],
'score': round(p[4], 5)}
jdict.append(result)
#evaluator.add([result])
#if evaluator.cache_exists:
# break
# # Assign all predictions as incorrect
# correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
# if nl:
# detected = [] # target indices
# tcls_tensor = labels[:, 0]
#
# # target boxes
# tbox = xywh2xyxy(labels[:, 1:5]) * whwh
#
# # Per target class
# for cls in torch.unique(tcls_tensor):
# ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1) # prediction indices
# pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1) # target indices
#
# # Search for detections
# if pi.shape[0]:
# # Prediction to target ious
# ious, i = box_iou(pred[pi, :4], tbox[ti]).max(1) # best ious, indices
#
# # Append detections
# detected_set = set()
# for j in (ious > iouv[0]).nonzero(as_tuple=False):
# d = ti[i[j]] # detected target
# if d.item() not in detected_set:
# detected_set.add(d.item())
# detected.append(d)
# correct[pi[j]] = ious[j] > iouv # iou_thres is 1xn
# if len(detected) == nl: # all targets already located in image
# break
#
# # Append statistics (correct, conf, pcls, tcls)
# stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))
# # Plot images
# if batch_i < 1:
# f = Path(save_dir) / ('test_batch%g_gt.jpg' % batch_i) # filename
# plot_images(img, targets, paths, str(f), names) # ground truth
# f = Path(save_dir) / ('test_batch%g_pred.jpg' % batch_i)
# plot_images(img, output_to_target(output, width, height), paths, str(f), names) # predictions
evaluator.add(jdict)
evaluator.save()
# # Compute statistics
# stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy
# if len(stats) and stats[0].any():
# p, r, ap, f1, ap_class = ap_per_class(*stats)
# p, r, ap50, ap = p[:, 0], r[:, 0], ap[:, 0], ap.mean(1) # [P, R, AP@0.5, AP@0.5:0.95]
# mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
# nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class
# else:
# nt = torch.zeros(1)
#
# # Print results
# pf = '%20s' + '%12.3g' * 6 # print format
# print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
#
# # Print results per class
# if verbose and nc > 1 and len(stats):
# for i, c in enumerate(ap_class):
# 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, t0 + t1)) + (imgsz, imgsz, batch_size) # tuple
# if not training:
# print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
#
# # Save JSON
# if save_json and len(jdict):
# f = 'detections_val2017_%s_results.json' % \
# (weights.split(os.sep)[-1].replace('.pt', '') if isinstance(weights, str) else '') # filename
# print('\nCOCO mAP with pycocotools... saving %s...' % f)
# with open(f, 'w') as file:
# json.dump(jdict, file)
#
# try: # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
# from pycocotools.coco import COCO
# from pycocotools.cocoeval import COCOeval
#
# imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]
# cocoGt = COCO(glob.glob('../coco/annotations/instances_val*.json')[0]) # initialize COCO ground truth api
# cocoDt = cocoGt.loadRes(f) # initialize COCO pred api
# cocoEval = COCOeval(cocoGt, cocoDt, 'bbox')
# cocoEval.params.imgIds = imgIds # image IDs to evaluate
# cocoEval.evaluate()
# cocoEval.accumulate()
# cocoEval.summarize()
# map, map50 = cocoEval.stats[:2] # update results (mAP@0.5:0.95, mAP@0.5)
# except Exception as e:
# print('ERROR: pycocotools unable to run: %s' % e)
#
# # Return results
# model.float() # for training
# maps = np.zeros(nc) + map
# for i, c in enumerate(ap_class):
# maps[c] = ap[i]
# return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
if __name__ == '__main__':
parser = argparse.ArgumentParser(prog='test.py')
parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
parser.add_argument('--data', type=str, default='data/coco.yaml', help='*.data path')
parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch')
parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float, default=0.65, help='IOU threshold for NMS')
parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
parser.add_argument('--task', default='val', help="'val', 'test', 'study'")
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
parser.add_argument('--augment', action='store_true', help='augmented inference')
parser.add_argument('--merge', action='store_true', help='use Merge NMS')
parser.add_argument('--verbose', action='store_true', help='report mAP by class')
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
opt = parser.parse_args()
opt.save_json |= opt.data.endswith('coco.yaml')
opt.data = check_file(opt.data) # check file
print(opt)
if opt.task in ['val', 'test']: # run normally
test(opt.data,
opt.weights,
opt.batch_size,
opt.img_size,
opt.conf_thres,
opt.iou_thres,
opt.save_json,
opt.single_cls,
opt.augment,
opt.verbose)
elif opt.task == 'study': # run over a range of settings and save/plot
for weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
f = 'study_%s_%s.txt' % (Path(opt.data).stem, Path(weights).stem) # filename to save to
x = list(range(320, 800, 64)) # x axis
y = [] # y axis
for i in x: # img-size
print('\nRunning %s point %s...' % (f, i))
r, _, t = test(opt.data, weights, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json)
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
# utils.general.plot_study_txt(f, x) # plot

30
test.py
View File

@ -2,7 +2,6 @@ import argparse
import glob
import json
import os
import shutil
from pathlib import Path
import numpy as np
@ -12,9 +11,9 @@ from tqdm import tqdm
from models.experimental import attempt_load
from utils.datasets import create_dataloader
from utils.general import (
coco80_to_coco91_class, check_dataset, check_file, check_img_size, compute_loss, non_max_suppression, scale_coords,
xyxy2xywh, clip_coords, plot_images, xywh2xyxy, box_iou, output_to_target, ap_per_class, set_logging)
from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, compute_loss, \
non_max_suppression, scale_coords, xyxy2xywh, clip_coords, plot_images, xywh2xyxy, box_iou, output_to_target, \
ap_per_class, set_logging, increment_dir
from utils.torch_utils import select_device, time_synchronized
@ -46,16 +45,11 @@ def test(data,
device = select_device(opt.device, batch_size=batch_size)
save_txt = opt.save_txt # save *.txt labels
# Remove previous
if os.path.exists(save_dir):
shutil.rmtree(save_dir) # delete dir
os.makedirs(save_dir) # make new dir
if save_txt:
out = save_dir / 'autolabels'
if os.path.exists(out):
shutil.rmtree(out) # delete dir
os.makedirs(out) # make new dir
# Directories
if save_dir == Path('runs/test'): # if default
os.makedirs('runs/test', exist_ok=True) # make base
save_dir = Path(increment_dir(save_dir / 'exp', opt.name)) # increment run
os.makedirs(save_dir / 'labels' if save_txt else save_dir, exist_ok=True) # make new dir
# Load model
model = attempt_load(weights, map_location=device) # load FP32 model
@ -144,8 +138,8 @@ def test(data,
x[:, :4] = scale_coords(img[si].shape[1:], x[:, :4], shapes[si][0], shapes[si][1]) # to original
for *xyxy, conf, cls in x:
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
line = (cls, conf, *xywh) if save_conf else (cls, *xywh) # label format
with open(str(out / Path(paths[si]).stem) + '.txt', 'a') as f:
line = (cls, *xywh, conf) if save_conf else (cls, *xywh) # label format
with open(str(save_dir / 'labels' / Path(paths[si]).stem) + '.txt', 'a') as f:
f.write(('%g ' * len(line) + '\n') % line)
# W&B logging
@ -268,6 +262,7 @@ def test(data,
print('ERROR: pycocotools unable to run: %s' % e)
# Return results
print('Results saved to %s' % save_dir)
model.float() # for training
maps = np.zeros(nc) + map
for i, c in enumerate(ap_class):
@ -292,6 +287,7 @@ if __name__ == '__main__':
parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
parser.add_argument('--save-dir', type=str, default='runs/test', help='directory to save results')
parser.add_argument('--name', default='', help='name to append to --save-dir: i.e. runs/{N} -> runs/{N}_{name}')
opt = parser.parse_args()
opt.save_json |= opt.data.endswith('coco.yaml')
opt.data = check_file(opt.data) # check file
@ -313,8 +309,6 @@ if __name__ == '__main__':
save_conf=opt.save_conf,
)
print('Results saved to %s' % opt.save_dir)
elif opt.task == 'study': # run over a range of settings and save/plot
for weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
f = 'study_%s_%s.txt' % (Path(opt.data).stem, Path(weights).stem) # filename to save to

11
train.py
View File

@ -1,5 +1,6 @@
import argparse
import logging
import math
import os
import random
import shutil
@ -7,7 +8,6 @@ import time
from pathlib import Path
from warnings import warn
import math
import numpy as np
import torch.distributed as dist
import torch.nn as nn
@ -404,14 +404,14 @@ if __name__ == '__main__':
parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
parser.add_argument('--name', default='', help='renames experiment folder exp{N} to exp{N}_{name} if supplied')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
parser.add_argument('--logdir', type=str, default='runs/', help='logging directory')
parser.add_argument('--logdir', type=str, default='runs/train', help='logging directory')
parser.add_argument('--name', default='', help='name to append to --save-dir: i.e. runs/{N} -> runs/{N}_{name}')
parser.add_argument('--log-imgs', type=int, default=10, help='number of images for W&B logging, max 100')
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
@ -428,7 +428,7 @@ if __name__ == '__main__':
# Resume
if opt.resume: # resume an interrupted run
ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path
log_dir = Path(ckpt).parent.parent # runs/exp0
log_dir = Path(ckpt).parent.parent # runs/train/exp0
assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
with open(log_dir / 'opt.yaml') as f:
opt = argparse.Namespace(**yaml.load(f, Loader=yaml.FullLoader)) # replace
@ -467,14 +467,13 @@ if __name__ == '__main__':
if opt.global_rank in [-1, 0]:
# Tensorboard
logger.info(f'Start Tensorboard with "tensorboard --logdir {opt.logdir}", view at http://localhost:6006/')
tb_writer = SummaryWriter(log_dir=log_dir) # runs/exp0
tb_writer = SummaryWriter(log_dir=log_dir) # runs/train/exp0
# W&B
try:
import wandb
assert os.environ.get('WANDB_DISABLED') != 'true'
logger.info("Weights & Biases logging enabled, to disable set os.environ['WANDB_DISABLED'] = 'true'")
except (ImportError, AssertionError):
opt.log_imgs = 0
logger.info("Install Weights & Biases for experiment logging via 'pip install wandb' (recommended)")

36
tutorial.ipynb vendored
View File

@ -596,22 +596,22 @@
}
},
"source": [
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source inference/images/\n",
"Image(filename='inference/output/zidane.jpg', width=600)"
"!python detect.py --weights yolov5s.pt --img 640 --conf 0.25 --source data/images/\n",
"Image(filename='runs/detect/exp0/zidane.jpg', width=600)"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', img_size=640, iou_thres=0.45, save_conf=False, save_dir='inference/output', save_txt=False, source='inference/images/', update=False, view_img=False, weights=['yolov5s.pt'])\n",
"Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', img_size=640, iou_thres=0.45, save_conf=False, save_dir='runs/detect', save_txt=False, source='data/images/', update=False, view_img=False, weights=['yolov5s.pt'])\n",
"Using CUDA device0 _CudaDeviceProperties(name='Tesla V100-SXM2-16GB', total_memory=16130MB)\n",
"\n",
"Fusing layers... \n",
"Model Summary: 140 layers, 7.45958e+06 parameters, 0 gradients\n",
"image 1/2 /content/yolov5/inference/images/bus.jpg: 640x480 4 persons, 1 buss, 1 skateboards, Done. (0.012s)\n",
"image 2/2 /content/yolov5/inference/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.012s)\n",
"Results saved to inference/output\n",
"image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 buss, 1 skateboards, Done. (0.012s)\n",
"image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.012s)\n",
"Results saved to runs/detect/exp0\n",
"Done. (0.113s)\n"
],
"name": "stdout"
@ -640,7 +640,7 @@
"id": "4qbaa3iEcrcE"
},
"source": [
"Results are saved to `inference/output`. A full list of available inference sources:\n",
"Results are saved to `runs/detect`. A full list of available inference sources:\n",
"<img src=\"https://user-images.githubusercontent.com/26833433/98274798-2b7a7a80-1f94-11eb-91a4-70c73593e26b.jpg\" width=\"900\"> "
]
},
@ -887,7 +887,7 @@
"source": [
"Train a YOLOv5s model on [COCO128](https://www.kaggle.com/ultralytics/coco128) with dataset `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and **COCO, COCO128, and VOC datasets are downloaded automatically** on first use.\n",
"\n",
"All training results are saved to `runs/exp0` for the first experiment, then `runs/exp1`, `runs/exp2` etc. for subsequent experiments.\n"
"All training results are saved to `runs/train/exp0` for the first experiment, then `runs/exp1`, `runs/exp2` etc. for subsequent experiments.\n"
]
},
{
@ -969,7 +969,7 @@
"Analyzing anchors... anchors/target = 4.26, Best Possible Recall (BPR) = 0.9946\n",
"Image sizes 640 train, 640 test\n",
"Using 2 dataloader workers\n",
"Logging results to runs/exp0\n",
"Logging results to runs/train/exp0\n",
"Starting training for 3 epochs...\n",
"\n",
" Epoch gpu_mem box obj cls total targets img_size\n",
@ -986,8 +986,8 @@
" 2/2 3.17G 0.04445 0.06545 0.01666 0.1266 149 640: 100% 8/8 [00:01<00:00, 4.33it/s]\n",
" Class Images Targets P R mAP@.5 mAP@.5:.95: 100% 8/8 [00:02<00:00, 2.78it/s]\n",
" all 128 929 0.395 0.766 0.701 0.455\n",
"Optimizer stripped from runs/exp0/weights/last.pt, 15.2MB\n",
"Optimizer stripped from runs/exp0/weights/best.pt, 15.2MB\n",
"Optimizer stripped from runs/train/exp0/weights/last.pt, 15.2MB\n",
"Optimizer stripped from runs/train/exp0/weights/best.pt, 15.2MB\n",
"3 epochs completed in 0.005 hours.\n",
"\n"
],
@ -1030,7 +1030,7 @@
"source": [
"## Local Logging\n",
"\n",
"All results are logged by default to the `runs/exp0` directory, with a new directory created for each new training as `runs/exp1`, `runs/exp2`, etc. View train and test jpgs to see mosaics, labels/predictions and augmentation effects. Note a **Mosaic Dataloader** is used for training (shown below), a new concept developed by Ultralytics and first featured in [YOLOv4](https://arxiv.org/abs/2004.10934)."
"All results are logged by default to the `runs/train/exp0` directory, with a new directory created for each new training as `runs/exp1`, `runs/exp2`, etc. View train and test jpgs to see mosaics, labels/predictions and augmentation effects. Note a **Mosaic Dataloader** is used for training (shown below), a new concept developed by Ultralytics and first featured in [YOLOv4](https://arxiv.org/abs/2004.10934)."
]
},
{
@ -1039,9 +1039,9 @@
"id": "riPdhraOTCO0"
},
"source": [
"Image(filename='runs/exp0/train_batch0.jpg', width=800) # train batch 0 mosaics and labels\n",
"Image(filename='runs/exp0/test_batch0_gt.jpg', width=800) # test batch 0 ground truth\n",
"Image(filename='runs/exp0/test_batch0_pred.jpg', width=800) # test batch 0 predictions"
"Image(filename='runs/train/exp0/train_batch0.jpg', width=800) # train batch 0 mosaics and labels\n",
"Image(filename='runs/train/exp0/test_batch0_gt.jpg', width=800) # test batch 0 ground truth\n",
"Image(filename='runs/train/exp0/test_batch0_pred.jpg', width=800) # test batch 0 predictions"
],
"execution_count": null,
"outputs": []
@ -1078,7 +1078,7 @@
},
"source": [
"from utils.utils import plot_results \n",
"plot_results(save_dir='runs/exp0') # plot results.txt as results.png\n",
"plot_results(save_dir='runs/train/exp0') # plot results.txt as results.png\n",
"Image(filename='results.png', width=800) "
],
"execution_count": null,
@ -1170,9 +1170,9 @@
" for di in 0 cpu # inference devices\n",
" do\n",
" python detect.py --weights $x.pt --device $di # detect official\n",
" python detect.py --weights runs/exp0/weights/last.pt --device $di # detect custom\n",
" python detect.py --weights runs/train/exp0/weights/last.pt --device $di # detect custom\n",
" python test.py --weights $x.pt --device $di # test official\n",
" python test.py --weights runs/exp0/weights/last.pt --device $di # test custom\n",
" python test.py --weights runs/train/exp0/weights/last.pt --device $di # test custom\n",
" done\n",
" python models/yolo.py --cfg $x.yaml # inspect\n",
" python models/export.py --weights $x.pt --img 640 --batch 1 # export\n",

10
utils/general.py
View File

@ -955,9 +955,15 @@ def increment_dir(dir, comment=''):
# Increments a directory runs/exp1 --> runs/exp2_comment
n = 0 # number
dir = str(Path(dir)) # os-agnostic
if os.path.isdir(dir):
stem = ''
dir += os.sep # removed by Path
else:
stem = Path(dir).stem
dirs = sorted(glob.glob(dir + '*')) # directories
if dirs:
matches = [re.search(r"exp(\d+)", d) for d in dirs]
matches = [re.search(r"%s(\d+)" % stem, d) for d in dirs]
idxs = [int(m.groups()[0]) for m in matches if m]
if idxs:
n = max(idxs) + 1 # increment
@ -1262,7 +1268,7 @@ def plot_results_overlay(start=0, stop=0): # from utils.general import *; plot_
def plot_results(start=0, stop=0, bucket='', id=(), labels=(), save_dir=''):
# from utils.general import *; plot_results(save_dir='runs/exp0')
# from utils.general import *; plot_results(save_dir='runs/train/exp0')
# Plot training 'results*.txt' as seen in https://github.com/ultralytics/yolov5#reproduce-our-training
fig, ax = plt.subplots(2, 5, figsize=(12, 6))
ax = ax.ravel()