Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 🐾 Cat vs Dog Classifier
|
| 2 |
|
| 3 |
This model is a deep convolutional neural network (CNN) built using PyTorch to classify images as either cats or dogs. It was trained on a labeled dataset of cat and dog images resized to 224×224 pixels, with extensive data augmentation and regularization techniques to improve generalization. The model achieves over 90% accuracy on the test set.
|
|
@@ -80,22 +99,3 @@ This model is licensed under the Apache 2.0 License. You are free to use, modify
|
|
| 80 |
|
| 81 |
Created by Sathvik as part of a deep learning exploration project focused on image classification and CNN architecture optimization.
|
| 82 |
|
| 83 |
-
|
| 84 |
-
---
|
| 85 |
-
license: apache-2.0
|
| 86 |
-
tags:
|
| 87 |
-
- image-classification
|
| 88 |
-
- cnn
|
| 89 |
-
- pytorch
|
| 90 |
-
- cat-vs-dog
|
| 91 |
-
- deep-learning
|
| 92 |
-
library_name: pytorch
|
| 93 |
-
datasets:
|
| 94 |
-
- custom
|
| 95 |
-
metrics:
|
| 96 |
-
- name: accuracy
|
| 97 |
-
type: accuracy
|
| 98 |
-
value: 90.56
|
| 99 |
-
model_name: Cat vs Dog Classifier
|
| 100 |
-
pipeline_tag: image-classification
|
| 101 |
-
---
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- image-classification
|
| 5 |
+
- cnn
|
| 6 |
+
- pytorch
|
| 7 |
+
- cat-vs-dog
|
| 8 |
+
- deep-learning
|
| 9 |
+
library_name: pytorch
|
| 10 |
+
datasets:
|
| 11 |
+
- custom
|
| 12 |
+
metrics:
|
| 13 |
+
- name: accuracy
|
| 14 |
+
type: accuracy
|
| 15 |
+
value: 90.56
|
| 16 |
+
model_name: Cat vs Dog Classifier
|
| 17 |
+
pipeline_tag: image-classification
|
| 18 |
+
---
|
| 19 |
+
---
|
| 20 |
# 🐾 Cat vs Dog Classifier
|
| 21 |
|
| 22 |
This model is a deep convolutional neural network (CNN) built using PyTorch to classify images as either cats or dogs. It was trained on a labeled dataset of cat and dog images resized to 224×224 pixels, with extensive data augmentation and regularization techniques to improve generalization. The model achieves over 90% accuracy on the test set.
|
|
|
|
| 99 |
|
| 100 |
Created by Sathvik as part of a deep learning exploration project focused on image classification and CNN architecture optimization.
|
| 101 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|