File size: 6,321 Bytes
19b0f3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65e7bd1
 
 
19b0f3b
65e7bd1
19b0f3b
 
 
92db551
9ec4feb
 
92db551
 
 
19b0f3b
92db551
 
 
9ec4feb
 
92db551
19b0f3b
92db551
 
 
 
 
19b0f3b
92db551
 
 
 
 
19b0f3b
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
# data_uploader.py
import streamlit as st
import pandas as pd
import numpy as np
from PIL import Image
import torch
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from datasets import Dataset as HFDataset, DatasetDict 
from huggingface_hub import HfApi  # For Hugging Face Hub interaction
import os

# Hugging Face Hub credentials
HF_TOKEN = os.getenv("HF_TOKEN")  
REPO_ID = "louiecerv/american_sign_language"  # Replace with your dataset repo name

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
st.write(f"Enabled GPU = {torch.cuda.is_available()}")

class MyDataset(Dataset):
        def __init__(self, x_df, y_df):
            self.xs = torch.tensor(x_df, dtype=torch.float32).to(device)  # Explicitly set dtype
            self.ys = torch.tensor(y_df, dtype=torch.long).to(device) # Explicitly set dtype

        def __getitem__(self, idx):
            x = self.xs[idx]
            y = self.ys[idx]
            return x, y

        def __len__(self):
            return len(self.xs)

# Load the dataset and convert to Hugging Face Dataset
def load_and_convert_to_hf_dataset(x, y, split="train"):
    df = pd.DataFrame({"image": list(x), "label": y})  # Create a DataFrame
    hf_dataset = HFDataset.from_pandas(df)

    # Preprocess images (Important for Hugging Face)
    def preprocess_function(examples):
        images = [np.array(img).reshape(28, 28) for img in examples["image"]] #Reshape the image
        # Convert to PIL images and apply transformations
        transformed_images = []
        for image in images:
            image = Image.fromarray(image.astype('uint8'))
            transform = transforms.Compose([
                transforms.Grayscale(num_output_channels=1),
                transforms.Resize((28, 28)),
                transforms.ToTensor(),
                transforms.Normalize(mean=[0.5], std=[0.5])
            ])
            transformed_image = transform(image)
            transformed_images.append(transformed_image)
        examples["pixel_values"] = torch.stack(transformed_images) #Stack the images into a tensor
        return examples

    hf_dataset = hf_dataset.map(preprocess_function, batched=True, remove_columns=["image"])
    hf_dataset.set_format("torch")  # Set format to PyTorch
    return hf_dataset

def upload_dataset_to_hub(dataset, repo_id):
    api = HfApi(token=HF_TOKEN)
    api.create_repo(repo_id, repo_type="dataset", exist_ok=True)  # Create repo if it doesn't exist
    dataset.push_to_hub(repo_id)
    print(f"Dataset uploaded to {repo_id}")


def main():
    st.title("American Sign Language Dataset Uploader")
    
    about = """
## About This App

This app is designed to load, preprocess, and upload datasets to the Hugging Face Hub. The main functionalities are encapsulated in the following components:

### Custom Dataset Class

The `MyDataset` class inherits from `torch.utils.data.Dataset` and is used to handle the dataset.

- **Initialization (`__init__`)**:
  - Converts input dataframes `x_df` and `y_df` to PyTorch tensors with explicit data types (`float32` for features and `long` for labels).
  - Moves the tensors to the specified device (e.g., GPU).

- **Get Item (`__getitem__`)**:
  - Retrieves the feature (`x`) and label (`y`) tensors at a given index `idx`.

- **Length (`__len__`)**:
  - Returns the length of the dataset.

### Load and Convert to Hugging Face Dataset

The `load_and_convert_to_hf_dataset` function converts input data into a Hugging Face dataset.

- **DataFrame Creation**:
  - Creates a Pandas DataFrame from the input features (`x`) and labels (`y`).

- **Preprocessing Function**:
  - Reshapes images to 28x28 pixels.
  - Converts images to PIL format and applies transformations (grayscale, resize, tensor conversion, and normalization).
  - Stacks the transformed images into a tensor.

- **Dataset Mapping**:
  - Applies the preprocessing function to the dataset.
  - Sets the dataset format to PyTorch.

### Data Loading and Conversion

The app loads training and validation data from CSV files and converts them into Hugging Face datasets.

- **Training Data**:
  - Loads data from `sign_mnist_train.csv`.
  - Separates features and labels.
  - Converts to a Hugging Face dataset.

- **Validation Data**:
  - Loads data from `sign_mnist_valid.csv`.
  - Separates features and labels.
  - Converts to a Hugging Face dataset.

### Upload Dataset to Hugging Face Hub

The `upload_dataset_to_hub` function uploads the dataset to the Hugging Face Hub.

- **Repository Creation**:
  - Creates a repository if it doesn't exist.

- **Dataset Upload**:
  - Pushes the dataset to the specified repository.

### Main Function

The `main` function orchestrates the entire process.

- Loads and preprocesses training and validation data.
- Creates a `DatasetDict` containing both datasets.
- Uploads the dataset to the Hugging Face Hub.

### Execution

The script is executed by calling the `main` function if the script is run as the main module.

```python
if __name__ == "__main__":
    main()"""

    with st.expander("About", expanded=True):
        st.write (about)

    st.write("## Instructions")
    st.write("Do not run this code on Huggingface.  Download the code and run it on your local machine.")
    st.write("Make sure you have the required files in the data/asl_data folder.")
    st.stop()

    try:

        # Load and convert dataframes to Hugging Face datasets
        train_df = pd.read_csv("data/asl_data/sign_mnist_train.csv")
        y_train = train_df.pop('label').values
        x_train = train_df.values

        valid_df = pd.read_csv("data/asl_data/sign_mnist_valid.csv")
        y_valid = valid_df.pop('label').values
        x_valid = valid_df.values
        
        train_dataset = load_and_convert_to_hf_dataset(x_train, y_train, "train")
        valid_dataset = load_and_convert_to_hf_dataset(x_valid, y_valid, "validation")

        # Create a DatasetDict
        full_dataset = DatasetDict({
            "train": train_dataset,
            "validation": valid_dataset
        })

        upload_dataset_to_hub(full_dataset, REPO_ID)  # Upload the DatasetDict
        st.write("Data upload complete.")

    except Exception as e:
        st.error(f"An error occurred: {e}")


if __name__ == "__main__":
    main()