TRY THIS MODEL
Drop image here to test
obj-detection-pcb-defects-yolov8/2 (latest)
Dataset Analytics
Generated on January 05, 2024 at 7:10 pm.
Number of Images
9,666
Number of Annotations
51,549
Average Image Size
0.41 mp
Median Image Ratio
640x640
square
Class Balance
Overview of the number of annotations for each class in your dataset.
Classes
all
train
valid
test
8,033
7,883
7,453
6,737
6,305
5,543
4,852
4,743
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
6320
6263
6029
5327
5050
4468
3911
3770
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
816
798
703
708
694
549
474
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
480
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
897
822
721
702
561
526
467
Add more images with this class to improve the model's ability to learn and predict it.
Under Represented
493
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.
All images are the same size, 640x640.
Aspect Ratio Distribution
The aspect ratio of your images compares the width vs. the height of your images.
square
9,666
Annotation Heatmap
Overview of where your annotations are located in the images in your dataset.
all
mousebite (7,883)
spur (6,305)
opencircuit (8,033)
scratch (5,543)
shortcircuit (6,737)
pinhole (7,453)
falsecopper (4,852)
missinghole (4,743)
Histogram of Object Count by Image
Overview of how many classes are annotated in each image in your dataset.
all
mousebite
spur
opencircuit
scratch
shortcircuit
pinhole
falsecopper
missinghole
-
1
-
2-3
-
4-5
-
6-7
-
8-9
-
10-11
-
12-13
3563 imgs
1781.5