- Notifications
You must be signed in to change notification settings - Fork8
Medical-AI is a AI framework specifically for Medical Applicationshttps://aibharata.github.io/medicalAI/
License
aibharata/medicalAI
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Medical-AI is a AI framework for rapid protyping for Medical Applications
Documentation:https://aibharata.github.io/medicalAI/
Source Code:https://github.com/aibharata/medicalai
Youtube Tutorial:https://www.youtube.com/V4nCX-kLACg
Medical-AI is a AI framework for rapid prototyping of AI for Medical Applications.
pipinstallmedicalai
Dependencies: Numpy, Tensorflow, Seaborn, Matplotlib, Pandas
NOTE: Dependency libraries are automatically installed. No need for user to install them manually.Getting Started Tutorial: Google ColabGoogle Colab Notebook Link
importmedicalaiasai
You can use the following templates to perform specific Tasks
Set the path of the dataset and set the target dimension of image that will be input to AI network.
trainSet,testSet,labelNames=ai.datasetFromFolder(datasetFolderPath,targetDim= (96,96)).load_dataset()
- trainSet contains 'data' and 'labels' accessible by trainSet.data and trainSet.labels- testSet contains 'data' and 'labels' accessible by testSet.data and testSet.labels- labelNames contains class names/labelsprint(trainSet.data.shape)print(trainSet.labels.shape)
trainer=ai.TRAIN_ENGINE()trainer.train_and_save_model(AI_NAME='tinyMedNet',MODEL_SAVE_NAME='PATH_WHERE_MODEL_IS_SAVED_TO',trainSet,testSet,OUTPUT_CLASSES,RETRAIN_MODEL=True,BATCH_SIZE=32,EPOCHS=10,LEARNING_RATE=0.001)
trainer.plot_train_acc_loss()
trainer.generate_evaluation_report()
PDF report will be generated with model sensitivity, specificity, accuracy, confidence intervals,ROC Curve Plot, Precision Recall Curve Plot, and Confusion Matrix Plot for each class.This function can be used when evaluating a model with Test or Validation Data Set.
trainer.explain(testSet.data[0:1],layer_to_explain='CNN3')
infEngine=ai.INFERENCE_ENGINE(modelName='PATH_WHERE_MODEL_IS_SAVED_TO')
infEngine.predict_with_labels(testSet.data[0:2],top_preds=3)
infEngine.predict(testSet.data[0:2])
infEngine.predict_pipeline(testSet.data[0:1])
## Setup AI Model Manager with required AI.model=ai.modelManager(AI_NAME=AI_NAME,modelName=MODEL_SAVE_NAME,x_train=train_data,OUTPUT_CLASSES=OUTPUT_CLASSES,RETRAIN_MODEL=RETRAIN_MODEL)# Start Trainingresult=ai.train(model,train_data,train_labels,BATCH_SIZE,EPOCHS,LEARNING_RATE,validation_data=(test_data,test_labels),callbacks=['tensorboard'])# Evaluate Trained Model on Test Datamodel.evaluate(test_data,test_labels)# Plot Accuracy vs Loss for Trainingai.plot_training_metrics(result)#Save the Trained Modelai.save_model_and_weights(model,outputName=MODEL_SAVE_NAME)
To Check the tests
pytestTo See Output of Print Statements
pytest -sDr. Vinayaka Jyothi
About
Medical-AI is a AI framework specifically for Medical Applicationshttps://aibharata.github.io/medicalAI/