nicholasKluge
commited on
Commit
•
0e27558
1
Parent(s):
24d29f6
Update README.md
Browse files
README.md
CHANGED
@@ -7,25 +7,11 @@ language:
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
---
|
|
|
10 |
|
11 |
-
|
12 |
|
13 |
-
##
|
14 |
-
|
15 |
-
The cats-vs-dogs model is a convolutional neural network (CNN) trained on the [Cats vs Dogs dataset](https://www.tensorflow.org/datasets/catalog/cats_vs_dogs),
|
16 |
-
a large set of images of cats and dogs.
|
17 |
-
|
18 |
-
### Details
|
19 |
-
|
20 |
-
- **Size:** 3,453,121 parameters
|
21 |
-
- **Model type:** CNN
|
22 |
-
- **Optimizer:** `RMSprop`
|
23 |
-
- **Number of Epochs:**
|
24 |
-
- **Hardware:** Tesla V4
|
25 |
-
- **Emissions:** Not measured
|
26 |
-
- **Total Energy Consumption:** Not measured
|
27 |
-
|
28 |
-
### How to Use
|
29 |
|
30 |
```python
|
31 |
!pip install huggingface_hub["tensorflow"] -q
|
@@ -37,72 +23,4 @@ import tensorflow as tf
|
|
37 |
model = from_pretrained_keras("AiresPucrs/cats-vs-dogs")
|
38 |
model.trainable = False
|
39 |
model.summary()
|
40 |
-
|
41 |
```
|
42 |
-
|
43 |
-
## Intended Use
|
44 |
-
|
45 |
-
This model was created for research purposes only. We do not recommend any application of this model outside this scope.
|
46 |
-
|
47 |
-
|
48 |
-
## Performance Metrics
|
49 |
-
|
50 |
-
Accuracy
|
51 |
-
|
52 |
-
## Training Data
|
53 |
-
|
54 |
-
[cats_vs_dogs dataset](https://www.tensorflow.org/datasets/catalog/cats_vs_dogs).
|
55 |
-
|
56 |
-
The dataset consists of a set of images of cats and dogs.
|
57 |
-
|
58 |
-
**Details:**
|
59 |
-
|
60 |
-
- [Homepage](https://www.microsoft.com/en-us/download/details.aspx?id=54765)
|
61 |
-
- Version: 1.0
|
62 |
-
- Date Published: 5/9/2022
|
63 |
-
- File Size:786.7 MB
|
64 |
-
|
65 |
-
## Training hyperparameters
|
66 |
-
|
67 |
-
The following hyperparameters were used during training:
|
68 |
-
|
69 |
-
| Hyperparameters | Value |
|
70 |
-
| :-- | :-- |
|
71 |
-
| name | RMSprop |
|
72 |
-
| learning_rate | 9.999999747378752e-05 |
|
73 |
-
| decay | 0.0 |
|
74 |
-
| rho | 0.8999999761581421 |
|
75 |
-
| momentum | 0.0 |
|
76 |
-
| epsilon | 1e-07 |
|
77 |
-
| centered | False |
|
78 |
-
| training_precision | float32 |
|
79 |
-
## Limitations
|
80 |
-
We do not recommend using this model in real-world applications. It was solely developed for academic and educational purposes.
|
81 |
-
|
82 |
-
## Cite as
|
83 |
-
|
84 |
-
```latex
|
85 |
-
@misc{teenytinycastle,
|
86 |
-
doi = {10.5281/zenodo.7112065},
|
87 |
-
url = {https://github.com/Nkluge-correa/teeny-tiny_castle},
|
88 |
-
author = {Nicholas Kluge Corr{\^e}a},
|
89 |
-
title = {Teeny-Tiny Castle},
|
90 |
-
year = {2024},
|
91 |
-
publisher = {GitHub},
|
92 |
-
journal = {GitHub repository},
|
93 |
-
}
|
94 |
-
```
|
95 |
-
|
96 |
-
## License
|
97 |
-
|
98 |
-
The cats-vs-dogs pre-trained model is under the Apache 2.0 License.
|
99 |
-
The cats_vs_dogs Dataset is licensed under the [Creative Commons(CC) License CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by/4.0/).
|
100 |
-
|
101 |
-
## Model Plot
|
102 |
-
|
103 |
-
<details>
|
104 |
-
<summary>View Model Plot</summary>
|
105 |
-
|
106 |
-
![Model Image](./model.png)
|
107 |
-
|
108 |
-
</details>
|
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
---
|
10 |
+
# Cats vs Dogs CNN (Teeny-Tiny Castle)
|
11 |
|
12 |
+
This model is part of a tutorial tied to the [Teeny-Tiny Castle](https://github.com/Nkluge-correa/TeenyTinyCastle), an open-source repository containing educational tools for AI Ethics and Safety research.
|
13 |
|
14 |
+
## How to Use
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
|
16 |
```python
|
17 |
!pip install huggingface_hub["tensorflow"] -q
|
|
|
23 |
model = from_pretrained_keras("AiresPucrs/cats-vs-dogs")
|
24 |
model.trainable = False
|
25 |
model.summary()
|
|
|
26 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|