Spaces:
Sleeping
Sleeping
updating some configs and typos in readme
Browse files
README.md
CHANGED
@@ -1,18 +1,20 @@
|
|
1 |
---
|
2 |
title: Mnist Comparison
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: streamlit
|
7 |
sdk_version: 1.37.0
|
|
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
|
|
11 |
---
|
12 |
|
13 |
# MNIST Streamlit
|
14 |
|
15 |
-
This is a simple Streamlit app that demonstrates the differences between neural nets trained on the MNIST
|
16 |
|
17 |
There are three models saved locally available in the `models` directory:
|
18 |
|
@@ -40,6 +42,10 @@ Once you draw a digit, the model will be loaded, asked to make a prediction on y
|
|
40 |
- The time it took to load the model
|
41 |
- The probability distribution of predictions as a bar chart and table
|
42 |
|
|
|
|
|
|
|
|
|
43 |
## Usage
|
44 |
|
45 |
To run the Streamlit app locally using Poetry, clone the repository, `cd` into the created directory, and run the following commands:
|
|
|
1 |
---
|
2 |
title: Mnist Comparison
|
3 |
+
emoji: π
|
4 |
+
colorFrom: yellow
|
5 |
+
colorTo: red
|
6 |
sdk: streamlit
|
7 |
sdk_version: 1.37.0
|
8 |
+
python_version: 3.12
|
9 |
app_file: app.py
|
10 |
pinned: false
|
11 |
license: mit
|
12 |
+
tags: MNIST, Onnx, Keras
|
13 |
---
|
14 |
|
15 |
# MNIST Streamlit
|
16 |
|
17 |
+
This is a simple Streamlit app that demonstrates the differences between neural nets trained on the [MNIST dataset](https://yann.lecun.com/exdb/mnist/).
|
18 |
|
19 |
There are three models saved locally available in the `models` directory:
|
20 |
|
|
|
42 |
- The time it took to load the model
|
43 |
- The probability distribution of predictions as a bar chart and table
|
44 |
|
45 |
+
If you change your selected model after drawing the digit, that same drawing will be used with the newly selected model.
|
46 |
+
|
47 |
+
To clear your "hand" drawn digit, click the trashcan icon under the drawing canvas.
|
48 |
+
|
49 |
## Usage
|
50 |
|
51 |
To run the Streamlit app locally using Poetry, clone the repository, `cd` into the created directory, and run the following commands:
|