TRY THIS MODEL
Drop image here to test
ppe-detection-using-cv/3 (latest)
Dataset Analytics
Generated on July 13, 2023 at 7:59 pm.
Number of Images
2,156
Number of Annotations
11,271
Average Image Size
0.61 mp
Median Image Ratio
950x650
wide
Class Balance
Overview of the number of annotations for each class in your dataset.
Classes
all
train
valid
test
2,576
2,311
1,202
1,140
802
656
633
506
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
407
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
267
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
243
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
200
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
148
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
118
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
61
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
1786
1569
823
772
557
433
444
331
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
285
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
197
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
169
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
137
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
108
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
91
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
43
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
522
492
253
254
165
152
109
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
125
77
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
45
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
48
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
24
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
24
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
12
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
This class is missing from the split. Add more images with this class to balance the
dataset.
Missing
268
250
126
114
80
80
50
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
45
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
25
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
26
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
16
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
3
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
This class is missing from the split. Add more images with this class to balance the
dataset.
Missing
Dimension Insights
Overview of the sizes and aspect ratios of the images in your dataset.
Size Distribution
Sizes are based on the number of pixels in your images.
The purple box indicates the median width by median height image (950x650).
Aspect Ratio Distribution
The aspect ratio of your images compares the width vs. the height of your images.
tall
234
square
104
wide
1,770
very wide
39
> 1.5:1
extremely wide
9
> 2.5:1
Annotation Heatmap
Overview of where your annotations are located in the images in your dataset.
0 (2,311)
1 (118)
2 (802)
3 (2,576)
4 (1,202)
all
helmet on head (656)
vest on body (506)
Person (1,140)
helmet (633)
no-vest (148)
No goggles (1)
goggles (267)
vest (407)
goggles on eyes (200)
no-helmet (61)
Histogram of Object Count by Image
Overview of how many classes are annotated in each image in your dataset.
0
1
2
3
4
all
helmet on head
vest on body
Person
helmet
no-vest
No goggles
goggles
vest
goggles on eyes
no-helmet
-
1
-
2-6
-
7-11
-
12-16
-
17-21
-
22-26
-
27-31
-
32-36
-
37-41
-
42-46
1598 imgs
799