Eehjie/fashion-mnist-tf-keras-model

👚 Fashion-MNIST Image Classifier (Keras, TensorFlow)

This is a simple image classification model trained on the Fashion-MNIST dataset using TensorFlow and Keras.

Fashion-MNIST is a drop-in replacement for the original MNIST digits dataset — but with images of clothes instead (10 classes of fashion items).

📊 Model Details

• Architecture: Fully connected neural network
• Framework: TensorFlow / Keras
• Input shape: 28x28 grayscale images
• Output classes: 10 fashion categories

Label	Class
0	T-shirt/top
1	Trouser
2	Pullover
3	Dress
4	Coat
5	Sandal
6	Shirt
7	Sneaker
8	Bag
9	Ankle boot

🧠 Training

• Dataset: Fashion-MNIST (60,000 training + 10,000 test images)
• Epochs: 5+
• Optimizer: Adam
• Loss function: Sparse Categorical Crossentropy
• Accuracy: ~88–91% on test set depending on tuning

🚀 Usage (Keras)

from huggingface_hub import hf_hub_download
import tensorflow as tf

# Download model file
model_path = hf_hub_download(
    repo_id="Eehjie/fashion-mnist-tf-keras-model",
    filename="fashion_mnist_model.h5"
)

# Load and compile
model = tf.keras.models.load_model(model_path)
model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])

# Predict
pred = model.predict(some_image_batch)  # input shape: (N, 28, 28)