Cats & Dogs Classifier
This model is a simple neural network trained to classify images of cats and dogs. It is built using PyTorch and trained on the louiecerv/cats_dogs_dataset dataset.
Model Details
- Architecture: Fully connected neural network
- Input Size: 128x128 RGB images
- Number of Classes: 2 (Cats & Dogs)
- Optimizer: Adam
- Loss Function: CrossEntropyLoss
- Training Epochs: 5
- Dataset: Cats & Dogs Dataset
Training
The model was trained using a basic fully connected neural network with ReLU activation functions. The training process involved using the Adam optimizer with a learning rate of 0.001.
Usage
import torch
from model import ImageClassifier
model = ImageClassifier(input_size=128*128*3, n_classes=2)
model.load_state_dict(torch.load("cats_dogs_classifier.pth"))
model.eval()
License
This model is released under the MIT license.
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the HF Inference API does not support torch models with pipeline type image-classification