Skip to content

Latest commit

 

History

History
25 lines (17 loc) · 942 Bytes

README.md

File metadata and controls

25 lines (17 loc) · 942 Bytes

Mini Project - Classification using pytorch

Covid-19-Detection-with-Chest-X-Ray-using-PyTorch

Use Pytorch to create and train a ResNet-18 model and apply it to check X Ray Radiography Dataset to classify the X rays into three classes 'Normal', 'Viral Pneumonia', 'COVID'.

Dataset: Chest X-Ray Radiography Dataset

  1. Import Packages and Libraries (torch, torchvision, numpy, matplotlib, PIL, random)
  2. Creating Custom Dataset - Pytorch Format
  3. Image Transformations (torchvision.transforms)
  4. Prepare Dataloader (torch.utils.data.Dataloader)
  5. Data Visualization - Plotting (Matplotlib)
  6. Creating the Model (resnet18 - pretrained)
  7. Training the Model (training the model until we get 95% accuracy)
  8. Final Results (predictions)

Hyperparameters:

Optimizer : Adams Optimizer

Learning Rate : 3e-5

Betas = (0.9,0.999)

Batch Size – 28