Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 🎮 GameNet-1
|
| 2 |
|
| 3 |
**GameNet-1** is a deep learning-based computer vision system designed to recognize video games based on their cover art or in-game screenshots. Built using EfficientNet and trained on a curated dataset of popular Steam games, the model predicts both the **game name** and its **genre(s)**.
|
|
@@ -47,5 +59,4 @@
|
|
| 47 |
- `Adam` optimizer (1e-3 for frozen, 1e-5 for fine-tune)
|
| 48 |
- Real-time data augmentation (`ImageDataGenerator`)
|
| 49 |
|
| 50 |
-
---
|
| 51 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- FronkonGames/steam-games-dataset
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
base_model:
|
| 8 |
+
- google/efficientnet-b3
|
| 9 |
+
pipeline_tag: image-classification
|
| 10 |
+
tags:
|
| 11 |
+
- game
|
| 12 |
+
---
|
| 13 |
# 🎮 GameNet-1
|
| 14 |
|
| 15 |
**GameNet-1** is a deep learning-based computer vision system designed to recognize video games based on their cover art or in-game screenshots. Built using EfficientNet and trained on a curated dataset of popular Steam games, the model predicts both the **game name** and its **genre(s)**.
|
|
|
|
| 59 |
- `Adam` optimizer (1e-3 for frozen, 1e-5 for fine-tune)
|
| 60 |
- Real-time data augmentation (`ImageDataGenerator`)
|
| 61 |
|
| 62 |
+
---
|
|
|