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

v3.0 Release (#725)

Browse Source 
* initial commit

* remove yolov3-spp from test.py study

* update study --img range

* update mAP

* cleanup and speed updates

* update README plot
pull/1/head
Glenn Jocher 5 years ago committed by GitHub
parent 1ddf692bf8
commit 916d4aad9a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
11 changed files with 43 additions and 40 deletions
Show Stats Download Patch File Download Diff File

3
Dockerfile
Unescape View File

@ -23,6 +23,7 @@ COPY . /usr/src/app
# Build and Push
# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
# for v in {300..303}; do t=ultralytics/coco:v$v && sudo docker build -t $t . && sudo docker push $t; done
# Pull and Run
# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host $t
@ -43,7 +44,7 @@ COPY . /usr/src/app
# sudo docker commit 092b16b25c5b usr/resume && sudo docker run -it --gpus all --ipc=host -v "$(pwd)"/coco:/usr/src/coco --entrypoint=sh usr/resume
# Send weights to GCP
# python -c "from utils.general import *; strip_optimizer('runs/exp0_*/weights/last.pt', 'tmp.pt')" && gsutil cp tmp.pt gs://*
# python -c "from utils.general import *; strip_optimizer('runs/exp0_*/weights/best.pt', 'tmp.pt')" && gsutil cp tmp.pt gs://*.pt
# Clean up
# docker system prune -a --volumes

28
README.md
Unescape View File

@ -6,8 +6,9 @@
This repository represents Ultralytics open-source research into future object detection methods, and incorporates our lessons learned and best practices evolved over training thousands of models on custom client datasets with our previous YOLO repository https://github.com/ultralytics/yolov3. **All code and models are under active development, and are subject to modification or deletion without notice.** Use at your own risk.
<img src="https://user-images.githubusercontent.com/26833433/85340570-30360a80-b49b-11ea-87cf-bdf33d53ae15.png" width="1000">** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 8, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS.
<img src="https://user-images.githubusercontent.com/26833433/90187293-6773ba00-dd6e-11ea-8f90-cd94afc0427f.png" width="1000">** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. EfficientDet data from [google/automl](https://github.com/google/automl) at batch size 8.
- **August 13, 2020**: [v3.0 release](https://github.com/ultralytics/yolov5/releases/tag/v3.0): nn.Hardswish() activations, data autodownload, native AMP.
- **July 23, 2020**: [v2.0 release](https://github.com/ultralytics/yolov5/releases/tag/v2.0): improved model definition, training and mAP.
- **June 22, 2020**: [PANet](https://arxiv.org/abs/1803.01534) updates: new heads, reduced parameters, improved speed and mAP [364fcfd](https://github.com/ultralytics/yolov5/commit/364fcfd7dba53f46edd4f04c037a039c0a287972).
- **June 19, 2020**: [FP16](https://pytorch.org/docs/stable/nn.html#torch.nn.Module.half) as new default for smaller checkpoints and faster inference [d4c6674](https://github.com/ultralytics/yolov5/commit/d4c6674c98e19df4c40e33a777610a18d1961145).
@ -20,19 +21,20 @@ This repository represents Ultralytics open-source research into future object d
| Model | AP<sup>val</sup> | AP<sup>test</sup> | AP<sub>50</sub> | Speed<sub>GPU</sub> | FPS<sub>GPU</sub> || params | FLOPS |
|---------- |------ |------ |------ | -------- | ------| ------ |------ | :------: |
| [YOLOv5s](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) | 36.1 | 36.1 | 55.3 | **2.1ms** | **476** || 7.5M | 13.2B
| [YOLOv5m](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) | 43.5 | 43.5 | 62.5 | 3.0ms | 333 || 21.8M | 39.4B
| [YOLOv5l](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) | 47.0 | 47.1 | 65.6 | 3.9ms | 256 || 47.8M | 88.1B
| [YOLOv5x](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) | **49.0** | **49.0** | **67.4** | 6.1ms | 164 || 89.0M | 166.4B
| [YOLOv5s](https://github.com/ultralytics/yolov5/releases/tag/v3.0) | 37.0 | 37.0 | 56.2 | **2.4ms** | **476** || 7.5M | 13.2B
| [YOLOv5m](https://github.com/ultralytics/yolov5/releases/tag/v3.0) | 44.3 | 44.3 | 63.2 | 3.4ms | 333 || 21.8M | 39.4B
| [YOLOv5l](https://github.com/ultralytics/yolov5/releases/tag/v3.0) | 47.7 | 47.7 | 66.5 | 4.4ms | 256 || 47.8M | 88.1B
| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/tag/v3.0) | **49.2** | **49.2** | **67.7** | 6.9ms | 164 || 89.0M | 166.4B
| | | | | | || |
| [YOLOv3-SPP](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) | 45.6 | 45.5 | 65.2 | 4.5ms | 222 || 63.0M | 118.0B
| [YOLOv5x](https://github.com/ultralytics/yolov5/releases/tag/v3.0) + TTA|**50.8**| **50.8** | **68.9** | 25.5ms | 39 || 89.0M | 354.3B
| | | | | | || |
| [YOLOv3-SPP](https://github.com/ultralytics/yolov5/releases/tag/v3.0) | 45.6 | 45.5 | 65.2 | 4.5ms | 222 || 63.0M | 118.0B
** AP<sup>test</sup> denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results in the table denote val2017 accuracy.
** All AP numbers are for single-model single-scale without ensemble or test-time augmentation. Reproduce by `python test.py --data coco.yaml --img 672 --conf 0.001`
** Speed<sub>GPU</sub> measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img. Reproduce by `python test.py --data coco.yaml --img 640 --conf 0.1`
** All AP numbers are for single-model single-scale without ensemble or test-time augmentation. **Reproduce** by `python test.py --data coco.yaml --img 640 --conf 0.001`
** Speed<sub>GPU</sub> measures end-to-end time per image averaged over 5000 COCO val2017 images using a GCP [n1-standard-16](https://cloud.google.com/compute/docs/machine-types#n1_standard_machine_types) instance with one V100 GPU, and includes image preprocessing, PyTorch FP16 image inference at --batch-size 32 --img-size 640, postprocessing and NMS. Average NMS time included in this chart is 1-2ms/img. **Reproduce** by `python test.py --data coco.yaml --img 640 --conf 0.1`
** All checkpoints are trained to 300 epochs with default settings and hyperparameters (no autoaugmentation).
** Test Time Augmentation ([TTA](https://github.com/ultralytics/yolov5/issues/303)) runs at 3 image sizes. **Reproduce** by `python test.py --data coco.yaml --img 832 --augment`
## Requirements
@ -98,11 +100,11 @@ Results saved to /content/yolov5/inference/output
## Training
Download [COCO](https://github.com/ultralytics/yolov5/blob/master/data/get_coco2017.sh) and run command below. Training times for YOLOv5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the largest `--batch-size` your GPU allows (batch sizes shown for 16 GB devices).
Download [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) and run command below. Training times for YOLOv5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the largest `--batch-size` your GPU allows (batch sizes shown for 16 GB devices).
```bash
$ python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
yolov5m 48
yolov5l 32
yolov5m 40
yolov5l 24
yolov5x 16
```
<img src="https://user-images.githubusercontent.com/26833433/84186698-c4d54d00-aa45-11ea-9bde-c632c1230ccd.png" width="900">

2
data/hyp.finetune.yaml
Unescape View File

@ -18,7 +18,7 @@ hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.5 # image translation (+/- fraction)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001

2
data/hyp.scratch.yaml
Unescape View File

@ -18,7 +18,7 @@ hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.5 # image translation (+/- fraction)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001

2
models/common.py
Unescape View File

@ -23,7 +23,7 @@ class Conv(nn.Module):
super(Conv, self).__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.LeakyReLU(0.1, inplace=True) if act else nn.Identity()
self.act = nn.Hardswish() if act else nn.Identity()
def forward(self, x):
return self.act(self.bn(self.conv(x)))

6
models/yolo.py
Unescape View File

@ -15,10 +15,13 @@ from utils.torch_utils import (
logger = logging.getLogger(__name__)
class Detect(nn.Module):
stride = None # strides computed during build
export = False # onnx export
def __init__(self, nc=80, anchors=(), ch=()): # detection layer
super(Detect, self).__init__()
self.stride = None # strides computed during build
self.nc = nc # number of classes
self.no = nc + 5 # number of outputs per anchor
self.nl = len(anchors) # number of detection layers
@ -28,7 +31,6 @@ class Detect(nn.Module):
self.register_buffer('anchors', a) # shape(nl,na,2)
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
self.export = False # onnx export
def forward(self, x):
# x = x.copy() # for profiling

6
test.py
Unescape View File

@ -280,9 +280,9 @@ if __name__ == '__main__':
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', 'yolov3-spp.pt']:
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(352, 832, 64)) # x axis
x = list(range(320, 800, 64)) # x axis
y = [] # y axis
for i in x: # img-size
print('\nRunning %s point %s...' % (f, i))
@ -290,4 +290,4 @@ if __name__ == '__main__':
y.append(r + t) # results and times
np.savetxt(f, y, fmt='%10.4g') # save
os.system('zip -r study.zip study_*.txt')
# plot_study_txt(f, x) # plot
# utils.general.plot_study_txt(f, x) # plot

7
train.py
Unescape View File

@ -30,6 +30,7 @@ from utils.torch_utils import init_seeds, ModelEMA, select_device, intersect_dic
logger = logging.getLogger(__name__)
def train(hyp, opt, device, tb_writer=None):
logger.info(f'Hyperparameters {hyp}')
log_dir = Path(tb_writer.log_dir) if tb_writer else Path(opt.logdir) / 'evolve' # logging directory
@ -131,7 +132,7 @@ def train(hyp, opt, device, tb_writer=None):
start_epoch = ckpt['epoch'] + 1
if epochs < start_epoch:
logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
(weights, ckpt['epoch'], epochs))
(weights, ckpt['epoch'], epochs))
epochs += ckpt['epoch'] # finetune additional epochs
del ckpt, state_dict
@ -404,7 +405,7 @@ if __name__ == '__main__':
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('--workers', type=int, default=8, help='maximum number of workers for dataloader')
parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
opt = parser.parse_args()
# Set DDP variables
@ -419,7 +420,7 @@ if __name__ == '__main__':
if last and not opt.weights:
logger.info(f'Resuming training from {last}')
opt.weights = last if opt.resume and not opt.weights else opt.weights
if opt.global_rank in [-1,0]:
if opt.global_rank in [-1, 0]:
check_git_status()
opt.hyp = opt.hyp or ('data/hyp.finetune.yaml' if opt.weights else 'data/hyp.scratch.yaml')

6
utils/activations.py
Unescape View File

@ -10,12 +10,6 @@ class Swish(nn.Module): #
return x * torch.sigmoid(x)
class HardSwish(nn.Module):
@staticmethod
def forward(x):
return x * F.hardtanh(x + 3, 0., 6., True) / 6.
class MemoryEfficientSwish(nn.Module):
class F(torch.autograd.Function):
@staticmethod

4
utils/datasets.py
Unescape View File

@ -610,7 +610,7 @@ def load_mosaic(self, index):
labels4 = []
s = self.img_size
yc, xc = s, s # mosaic center x, y
yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border] # mosaic center x, y
indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)] # 3 additional image indices
for i, index in enumerate(indices):
# Load image
@ -804,7 +804,7 @@ def random_perspective(img, targets=(), degrees=10, translate=.1, scale=.1, shea
return img, targets
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.2): # box1(4,n), box2(4,n)
def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1): # box1(4,n), box2(4,n)
# Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
w2, h2 = box2[2] - box2[0], box2[3] - box2[1]

17
utils/general.py
Unescape View File

@ -1147,7 +1147,7 @@ def plot_study_txt(f='study.txt', x=None): # from utils.general import *; plot_
ax = ax.ravel()
fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
for f in ['coco_study/study_coco_yolov5%s.txt' % x for x in ['s', 'm', 'l', 'x']]:
for f in ['study/study_coco_yolov5%s.txt' % x for x in ['s', 'm', 'l', 'x']]:
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)
s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_inference (ms/img)', 't_NMS (ms/img)', 't_total (ms/img)']
@ -1159,7 +1159,7 @@ def plot_study_txt(f='study.txt', x=None): # from utils.general import *; plot_
ax2.plot(y[6, :j], y[3, :j] * 1E2, '.-', linewidth=2, markersize=8,
label=Path(f).stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [33.8, 39.6, 43.0, 47.5, 49.4, 50.7],
ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
ax2.grid()
@ -1170,7 +1170,7 @@ def plot_study_txt(f='study.txt', x=None): # from utils.general import *; plot_
ax2.set_ylabel('COCO AP val')
ax2.legend(loc='lower right')
plt.savefig('study_mAP_latency.png', dpi=300)
plt.savefig(f.replace('.txt', '.png'), dpi=200)
plt.savefig(f.replace('.txt', '.png'), dpi=300)
def plot_labels(labels, save_dir=''):
@ -1247,8 +1247,11 @@ def plot_results(start=0, stop=0, bucket='', id=(), labels=(),
s = ['GIoU', 'Objectness', 'Classification', 'Precision', 'Recall',
'val GIoU', 'val Objectness', 'val Classification', 'mAP@0.5', 'mAP@0.5:0.95']
if bucket:
os.system('rm -rf storage.googleapis.com')
files = ['https://storage.googleapis.com/%s/results%g.txt' % (bucket, x) for x in id]
# os.system('rm -rf storage.googleapis.com')
# files = ['https://storage.googleapis.com/%s/results%g.txt' % (bucket, x) for x in id]
files = ['results%g.txt' % x for x in id]
c = ('gsutil cp ' + '%s ' * len(files) + '.') % tuple('gs://%s/results%g.txt' % (bucket, x) for x in id)
os.system(c)
else:
files = glob.glob(str(Path(save_dir) / 'results*.txt')) + glob.glob('../../Downloads/results*.txt')
for fi, f in enumerate(files):
@ -1266,8 +1269,8 @@ def plot_results(start=0, stop=0, bucket='', id=(), labels=(),
ax[i].set_title(s[i])
# if i in [5, 6, 7]: # share train and val loss y axes
# ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
except:
print('Warning: Plotting error for %s, skipping file' % f)
except Exception as e:
print('Warning: Plotting error for %s; %s' % (f, e))
fig.tight_layout()
ax[1].legend()

Write Preview
Loading…
Cancel
Save