Skip to content

Commit

Permalink
Add object detection files to XiNet as well (#59)
Browse files Browse the repository at this point in the history 
* fix linters

* fix credits

* add coco training configuration files
  • Loading branch information
@fpaissan
fpaissan authored Nov 28, 2023
1 parent 93cdcc6 commit 7460236
Show file tree
Hide file tree
Showing 6 changed files with 734 additions and 0 deletions.
151 changes: 151 additions & 0 deletions recipes/objection_detection/cfg/data/coco.yaml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,151 @@
########
# Data configuration file for COCO8 trainings.
# Based on the ultralytics data conf.
#
# Adapted by:
# - Matteo Beltrami, 2023
# - Francesco Paissan, 2023
########
task: detect # (str) YOLO task, i.e. detect, segment, classify, pose
mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark

# Train settings -------------------------------------------------------------------------------------------------------
imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val'
cache: False # (bool) True/ram, disk or False. Use cache for data loading
single_cls: False # (bool) train multi-class data as single-class
fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)

# Segmentation
overlap_mask: True # (bool) masks should overlap during training (segment train only)
mask_ratio: 4 # (int) mask downsample ratio (segment train only)

# Prediction settings --------------------------------------------------------------------------------------------------
classes: # (int | list[int], optional) filter results by class, i.e. classes=0, or classes=[0,2,3]

# Hyperparameters ------------------------------------------------------------------------------------------------------
box: 7.5 # (float) box loss gain
cls: 0.5 # (float) cls loss gain (scale with pixels)
dfl: 1.5 # (float) dfl loss gain

hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction)
degrees: 0.0 # (float) image rotation (+/- deg)
translate: 0.1 # (float) image translation (+/- fraction)
scale: 0.5 # (float) image scale (+/- gain)
shear: 0.0 # (float) image shear (+/- deg)
perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # (float) image flip up-down (probability)
fliplr: 0.5 # (float) image flip left-right (probability)
mosaic: 1.0 # (float) image mosaic (probability)
mixup: 0.0 # (float) image mixup (probability)
copy_paste: 0.0 # (float) segment copy-paste (probability)


# Dataset location
path: /mnt/data/coco # dataset root dir
train: train2017.txt # train images (relative to 'path') 118287 images
val: val2017.txt # val images (relative to 'path') 5000 images
test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794

# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush


# Download script/URL (optional)
download: |
from ultralytics.utils.downloads import download
from pathlib import Path
# Download labels
segments = True # segment or box labels
dir = Path(data_cfg['path']) # dataset root dir
url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')] # labels
download(urls, dir=dir.parent)
# Download data
urls = ['http://images.cocodataset.org/zips/train2017.zip', # 19G, 118k images
'http://images.cocodataset.org/zips/val2017.zip', # 1G, 5k images
'http://images.cocodataset.org/zips/test2017.zip'] # 7G, 41k images (optional)
download(urls, dir=dir / 'images', threads=3)
144 changes: 144 additions & 0 deletions recipes/objection_detection/cfg/data/coco8.yaml
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,144 @@
########
# Data configuration file for COCO8 trainings.
# Based on the ultralytics data conf.
#
# Adapted by:
# - Matteo Beltrami, 2023
# - Francesco Paissan, 2023
########
task: detect # (str) YOLO task, i.e. detect, segment, classify, pose
mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark

# Train settings -------------------------------------------------------------------------------------------------------
imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
rect: False # (bool) rectangular training if mode='train' or rectangular validation if mode='val'
cache: False # (bool) True/ram, disk or False. Use cache for data loading
single_cls: False # (bool) train multi-class data as single-class
fraction: 1.0 # (float) dataset fraction to train on (default is 1.0, all images in train set)

# Segmentation
overlap_mask: True # (bool) masks should overlap during training (segment train only)
mask_ratio: 4 # (int) mask downsample ratio (segment train only)

# Prediction settings --------------------------------------------------------------------------------------------------
classes: # (int | list[int], optional) filter results by class, i.e. classes=0, or classes=[0,2,3]

# Hyperparameters ------------------------------------------------------------------------------------------------------
box: 7.5 # (float) box loss gain
cls: 0.5 # (float) cls loss gain (scale with pixels)
dfl: 1.5 # (float) dfl loss gain

hsv_h: 0.015 # (float) image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # (float) image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # (float) image HSV-Value augmentation (fraction)
degrees: 0.0 # (float) image rotation (+/- deg)
translate: 0.1 # (float) image translation (+/- fraction)
scale: 0.5 # (float) image scale (+/- gain)
shear: 0.0 # (float) image shear (+/- deg)
perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # (float) image flip up-down (probability)
fliplr: 0.5 # (float) image flip left-right (probability)
mosaic: 1.0 # (float) image mosaic (probability)
mixup: 0.0 # (float) image mixup (probability)
copy_paste: 0.0 # (float) segment copy-paste (probability)


# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: /mnt/data/coco8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)

# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush

# Download script/URL (optional)
download: |
from pathlib import Path
import zipfile
import os
data_cfg['path'] = Path(data_cfg['path'])
os.makedirs(data_cfg["path"], exist_ok=True)
os.system(f"wget https://ultralytics.com/assets/coco8.zip -O {os.path.join(data_cfg['path'], 'coco8.zip')}")
with zipfile.ZipFile(os.path.join(data_cfg['path'], 'coco8.zip'), 'r') as zip_ref:
zip_ref.extractall(data_cfg['path'].parent)
20 changes: 20 additions & 0 deletions recipes/objection_detection/cfg/yolo_phinet.py
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
"""
YOLOPhiNet training configuration.
Authors:
- Matteo Beltrami, 2023
- Francesco Paissan, 2023
"""
# Data configuration
batch_size = 8
data_cfg = "cfg/data/coco.yaml"

# Model configuration
input_shape = (3, 672, 672)
alpha = 3
num_layers = 7
beta = 0.75
t_zero = 6
divisor = 8
downsampling_layers = [5, 7]
return_layers = [4, 6, 7]
Loading

0 comments on commit 7460236

Please sign in to comment.