Instructions to use DineshKumar1329/DogCat_Classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DineshKumar1329/DogCat_Classifier with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DineshKumar1329/DogCat_Classifier", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signaturecd19f58 -
Update README.md
Verified signature329e3e3 -
Update README.md
Verified signature522791f -
Update README.md
Verified signature1e171fb -
Update README.md
Verified signaturecad0b5f -
Update README.md
Verified signature924a4f6 -
Update README.md
Verified signatureae49adc -
Update README.md
Verified signature279f2f6 -
Upload config.json
Verified signature83d746a -
Upload config.json
Verified signature03a4b6c -
Update README.md
Verified signature0786365 -
Delete config.json
Verified signature7860160 -
Update README.md
Verified signaturef32744b -
Update README.md
Verified signatureb1f3701 -
Update README.md
Verified signature33c2832 -
Delete DogCat_Classifier
Verified signatureda5c6e7 -
Upload cat_dog_classifier.pth
Verified signatureca2135f -
Update README.md
Verified signature2845792 -
Rename cat_dog_classifier.pth to DogCat_Classifier
Verified signaturea758463 -
Upload config.json
Verified signatureccf7fd6 -
Update README.md
Verified signatureab6d81c -
Update README.md
Verified signatureea04e29 -
Update README.md
Verified signaturef0ebf06 -
Update README.md
Verified signature741c189 -
Update README.md
Verified signaturec7fdb40 -
Update README.md
Verified signaturea811d4c -
Update README.md
Verified signature# Dog and Cat Classification using DeepLearning - Implementing a deep learning pipeline for classifying images of cats and dogs using the PyTorch framework. It begins by preparing a dataset, visualizing class distributions, and splitting data into training and testing sets. Image preprocessing involves resizing, random transformations, and normalization. - The model architecture utilizes a pretrained ResNet-18 with the final layer adapted for binary classification (cats vs. dogs). Training involves defining a loss function (CrossEntropyLoss), an optimizer (Adam), and a learning rate scheduler. The training loop iterates through epochs, evaluating performance with training loss plotted over epochs. - After training, the model is evaluated on a test set to compute accuracy, achieving approximately 90.27% accuracy in this case. Trained model parameters are saved for future use. Inference capabilities include loading a single image, preprocessing it for prediction, and using the model to…8a48ffd -
Upload cat_dog_classifier.pth
Verified signature005efab -
initial commit
Verified signaturecc241a1