๐Ÿพ MozieFinder

MozieFinder is a lightweight convolutional neural network (CNN) model built from scratch using TensorFlow, designed to classify images as either cats or dogs.

  • ๐Ÿ“ฆ Model Type: Custom CNN (ResNet-inspired)
  • ๐Ÿถ๐Ÿฑ Task: Binary Image Classification (Cat vs. Dog)
  • ๐Ÿง  Trainable Parameters: ~1.2 million
  • ๐Ÿ–ผ๏ธ Input Resolution: 224x224
  • ๐Ÿ‹๏ธ Training Data: ~20,000 labeled cat and dog images
  • ๐ŸŽฏ Validation Accuracy: ~92%

MozieFinder was trained from scratch โ€” no pre-trained weights were used โ€” as a demonstration of how to build a robust image classification model end-to-end.

โš ๏ธ Disclaimer: This model card was written by the model creator. It has not been officially reviewed by TensorFlow or affiliated teams.

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Space using vadymkalin/MozieFinder-1.0.0 1