Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,6 @@ tags:
|
|
| 6 |
- tensorflow
|
| 7 |
- keras
|
| 8 |
- fashion-mnist
|
| 9 |
-
- academic-project
|
| 10 |
datasets:
|
| 11 |
- fashion_mnist
|
| 12 |
metrics:
|
|
@@ -16,10 +15,10 @@ metrics:
|
|
| 16 |
- f1
|
| 17 |
---
|
| 18 |
|
| 19 |
-
# Deep CNN for Fashion MNIST –
|
| 20 |
|
| 21 |
-
This model is part of a
|
| 22 |
-
Stage 3
|
| 23 |
|
| 24 |
## Architecture Summary
|
| 25 |
|
|
@@ -27,7 +26,7 @@ Stage 3 introduced architectural tuning with Batch Normalisation and Dropout for
|
|
| 27 |
- Batch Normalisation + ReLU after each
|
| 28 |
- MaxPooling after each block
|
| 29 |
- Dropout applied after conv blocks and dense layer
|
| 30 |
-
- Dense(128) → Dense(10)
|
| 31 |
|
| 32 |
## Evaluation Metrics (on Test Set)
|
| 33 |
|
|
|
|
| 6 |
- tensorflow
|
| 7 |
- keras
|
| 8 |
- fashion-mnist
|
|
|
|
| 9 |
datasets:
|
| 10 |
- fashion_mnist
|
| 11 |
metrics:
|
|
|
|
| 15 |
- f1
|
| 16 |
---
|
| 17 |
|
| 18 |
+
# Deep CNN for Fashion MNIST – Stage 3 Model Tuning
|
| 19 |
|
| 20 |
+
This model is part of a structured project focused on building and improving deep convolutional neural networks (CNNs) for clothing item classification using the Fashion MNIST dataset.
|
| 21 |
+
This is **Stage 3**, where architectural tuning with Batch Normalisation and Dropout was introduced to improve performance and generalisation.
|
| 22 |
|
| 23 |
## Architecture Summary
|
| 24 |
|
|
|
|
| 26 |
- Batch Normalisation + ReLU after each
|
| 27 |
- MaxPooling after each block
|
| 28 |
- Dropout applied after conv blocks and dense layer
|
| 29 |
+
- Dense(128) → Dense(10) with softmax output
|
| 30 |
|
| 31 |
## Evaluation Metrics (on Test Set)
|
| 32 |
|