Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,19 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
| 4 |
+
# Training dataset metadata:
|
| 5 |
+
1. Dataset classes: ['soft', 'digital', 'hard']
|
| 6 |
+
2. Number of classes: 3
|
| 7 |
+
3. Total number of images: 18415
|
| 8 |
+
## Number of images per class:
|
| 9 |
+
- soft : 5482
|
| 10 |
+
- digital : 1206
|
| 11 |
+
- hard : 11727
|
| 12 |
+
## Classes description:
|
| 13 |
+
The hard class contains the following categories of objects:
|
| 14 |
+
object, laptop, charger, pc mouse, pc, rocks, table, bed, box, sneakers, ship, wire, guitar, fork, spoon, plate, keyboard, car, bus, screwdriver, ball, door, flower, clocks, fruit , food, robot.
|
| 15 |
+
The soft class contains the following categories of objects:
|
| 16 |
+
animal, people, human, man, woman, t-shirt, hairs, hair, dog, cat, monkey, cow, medusa, clothes
|
| 17 |
+
The digital class contains the following categories of scenes: screenshot
|
| 18 |
+
## Architecture info
|
| 19 |
+
The classifier uses DenseNet161 as the encoder and some linear layers at classifier base.
|