Dataset download bash script updates (#1132)
Browse files- data/scripts/get_coco.sh +10 -7
- data/scripts/get_voc.sh +12 -68
data/scripts/get_coco.sh
CHANGED
@@ -8,14 +8,17 @@
|
|
8 |
# /yolov5
|
9 |
|
10 |
# Download/unzip labels
|
11 |
-
echo 'Downloading COCO 2017 labels ...'
|
12 |
d='../' # unzip directory
|
13 |
-
|
14 |
-
|
|
|
15 |
|
16 |
# Download/unzip images
|
17 |
-
echo 'Downloading COCO 2017 images ...'
|
18 |
d='../coco/images' # unzip directory
|
19 |
-
|
20 |
-
|
21 |
-
|
|
|
|
|
|
|
|
|
|
8 |
# /yolov5
|
9 |
|
10 |
# Download/unzip labels
|
|
|
11 |
d='../' # unzip directory
|
12 |
+
url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
|
13 |
+
f='coco2017labels.zip' # 68 MB
|
14 |
+
echo 'Downloading' $url$f ' ...' && curl -L $url$f -o $f && unzip -q $f -d $d && rm $f # download, unzip, remove
|
15 |
|
16 |
# Download/unzip images
|
|
|
17 |
d='../coco/images' # unzip directory
|
18 |
+
url=http://images.cocodataset.org/zips/
|
19 |
+
f1='train2017.zip' # 19G, 118k images
|
20 |
+
f2='val2017.zip' # 1G, 5k images
|
21 |
+
f3='test2017.zip' # 7G, 41k images (optional)
|
22 |
+
for f in $f1 $f2; do
|
23 |
+
echo 'Downloading' $url$f ' ...' && curl -L $url$f -o $f && unzip -q $f -d $d && rm $f # download, unzip, remove
|
24 |
+
done
|
data/scripts/get_voc.sh
CHANGED
@@ -8,79 +8,23 @@
|
|
8 |
# /yolov5
|
9 |
|
10 |
start=$(date +%s)
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
fi
|
24 |
-
echo "navigating to" $1 "..."
|
25 |
-
cd $1
|
26 |
-
fi
|
27 |
-
|
28 |
-
echo "Downloading VOC2007 trainval ..."
|
29 |
-
# Download data
|
30 |
-
curl -LO http://pjreddie.com/media/files/VOCtrainval_06-Nov-2007.tar
|
31 |
-
echo "Downloading VOC2007 test data ..."
|
32 |
-
curl -LO http://pjreddie.com/media/files/VOCtest_06-Nov-2007.tar
|
33 |
-
echo "Done downloading."
|
34 |
-
|
35 |
-
# Extract data
|
36 |
-
echo "Extracting trainval ..."
|
37 |
-
tar -xf VOCtrainval_06-Nov-2007.tar
|
38 |
-
echo "Extracting test ..."
|
39 |
-
tar -xf VOCtest_06-Nov-2007.tar
|
40 |
-
echo "removing tars ..."
|
41 |
-
rm VOCtrainval_06-Nov-2007.tar
|
42 |
-
rm VOCtest_06-Nov-2007.tar
|
43 |
-
|
44 |
-
end=$(date +%s)
|
45 |
-
runtime=$((end - start))
|
46 |
-
|
47 |
-
echo "Completed in" $runtime "seconds"
|
48 |
-
|
49 |
-
start=$(date +%s)
|
50 |
-
|
51 |
-
# handle optional download dir
|
52 |
-
if [ -z "$1" ]; then
|
53 |
-
# navigate to ~/tmp
|
54 |
-
echo "navigating to ../tmp/ ..."
|
55 |
-
mkdir -p ../tmp
|
56 |
-
cd ../tmp/
|
57 |
-
else
|
58 |
-
# check if is valid directory
|
59 |
-
if [ ! -d $1 ]; then
|
60 |
-
echo $1 "is not a valid directory"
|
61 |
-
exit 0
|
62 |
-
fi
|
63 |
-
echo "navigating to" $1 "..."
|
64 |
-
cd $1
|
65 |
-
fi
|
66 |
-
|
67 |
-
echo "Downloading VOC2012 trainval ..."
|
68 |
-
# Download data
|
69 |
-
curl -LO http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar
|
70 |
-
echo "Done downloading."
|
71 |
-
|
72 |
-
# Extract data
|
73 |
-
echo "Extracting trainval ..."
|
74 |
-
tar -xf VOCtrainval_11-May-2012.tar
|
75 |
-
echo "removing tar ..."
|
76 |
-
rm VOCtrainval_11-May-2012.tar
|
77 |
|
78 |
end=$(date +%s)
|
79 |
runtime=$((end - start))
|
80 |
-
|
81 |
echo "Completed in" $runtime "seconds"
|
82 |
|
83 |
-
cd ../tmp
|
84 |
echo "Spliting dataset..."
|
85 |
python3 - "$@" <<END
|
86 |
import xml.etree.ElementTree as ET
|
|
|
8 |
# /yolov5
|
9 |
|
10 |
start=$(date +%s)
|
11 |
+
mkdir -p ../tmp
|
12 |
+
cd ../tmp/
|
13 |
+
|
14 |
+
# Download/unzip images and labels
|
15 |
+
d='.' # unzip directory
|
16 |
+
url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
|
17 |
+
f1=VOCtrainval_06-Nov-2007.zip # 446MB, 5012 images
|
18 |
+
f2=VOCtest_06-Nov-2007.zip # 438MB, 4953 images
|
19 |
+
f3=VOCtrainval_11-May-2012.zip # 1.95GB, 17126 images
|
20 |
+
for f in $f1 $f2 $f3; do
|
21 |
+
echo 'Downloading' $url$f ' ...' && curl -L $url$f -o $f && unzip -q $f -d $d && rm $f # download, unzip, remove
|
22 |
+
done
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
end=$(date +%s)
|
25 |
runtime=$((end - start))
|
|
|
26 |
echo "Completed in" $runtime "seconds"
|
27 |
|
|
|
28 |
echo "Spliting dataset..."
|
29 |
python3 - "$@" <<END
|
30 |
import xml.etree.ElementTree as ET
|