Wolverine001 commited on
Commit
f1e3a6d
·
verified ·
1 Parent(s): ed14022

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +17 -15
README.md CHANGED
@@ -1,3 +1,4 @@
 
1
  ---
2
  language: en
3
  license: mit
@@ -5,26 +6,27 @@ datasets: [Cats-Dogs]
5
  metrics: [accuracy, f1, precision, recall]
6
  ---
7
 
8
- # Transfer Learning On Alexnet:
9
 
10
- This model uses Transfer Learning for a 2 labelled class Cats-Dogs classification.
11
 
12
- - Pre-trained model used: Alexnet.
13
- - Dataset used: Cats_Dogs.
14
- - batch_size = 8
15
- - learning_rate = 0.001
16
- - epochs = 5
 
17
 
18
- ## **Evaluation Results**
19
 
20
- ### 📌 **Before Transfer Learning**
 
 
 
 
21
 
22
- ** Accuracy:** 40.66%
23
- - Precision: 0.3983,
24
- - Recall: 0.4066,
25
- - F1-score: 0.3942,
26
 
27
- - Confusion Matrix:
28
  [[ 659 1841]
29
  [1126 1374]]
30
  ---
@@ -40,7 +42,7 @@ This model uses Transfer Learning for a 2 labelled class Cats-Dogs classificatio
40
  [1006 8994]]
41
 
42
 
43
- ** Validatio Accuracy:** 94.10%
44
  - Precision: 0.9425,
45
  - Recall: 0.9410,
46
  - F1-score: 0.9410,
 
1
+
2
  ---
3
  language: en
4
  license: mit
 
6
  metrics: [accuracy, f1, precision, recall]
7
  ---
8
 
9
+ # 🐱🐶 Transfer Learning on AlexNet for Cats vs. Dogs Classification
10
 
11
+ This model fine-tunes **AlexNet** using Transfer Learning to classify images into two categories: **Cats** and **Dogs**.
12
 
13
+ ## **📝 Model Details**
14
+ - **Pre-trained Model:** AlexNet
15
+ - **Dataset Used:** Cats-Dogs
16
+ - **Batch Size:** 8
17
+ - **Learning Rate:** 0.001
18
+ - **Epochs:** 5
19
 
20
+ ---
21
 
22
+ ## **📌 Baseline Performance (Before Transfer Learning)**
23
+ **Validation Accuracy:** **40.66%**
24
+ - **Precision:** 0.3983
25
+ - **Recall:** 0.4066
26
+ - **F1-score:** 0.3942
27
 
28
+ **Confusion Matrix:**
 
 
 
29
 
 
30
  [[ 659 1841]
31
  [1126 1374]]
32
  ---
 
42
  [1006 8994]]
43
 
44
 
45
+ ** Validation Accuracy:** 94.10%
46
  - Precision: 0.9425,
47
  - Recall: 0.9410,
48
  - F1-score: 0.9410,