Spaces:
Build error
Build error
| import gradio as gr | |
| from fastai.vision.all import * | |
| from efficientnet_pytorch import EfficientNet | |
| import torch, torchvision | |
| from torchvision import transforms | |
| from pytorch_grad_cam import GradCAM | |
| from pytorch_grad_cam.utils.image import show_cam_on_image | |
| from PIL import Image | |
| title = "COVID_19 Infection Detectation App!" | |
| head = ( | |
| "<body>" | |
| "<center>" | |
| "<img src='/file=Gradcam.png' width=200>" | |
| "<h2>" | |
| "This Space demonstrates a model based on efficientnetB7 base model. The Model was trained to classify chest xray image. To test it, " | |
| "</h2>" | |
| "<h3>" | |
| "Use the Example Images provided below the up or Upload your own xray images with the App." | |
| "</h3>" | |
| "<h3>" | |
| "!!!PLEASE NOTE MODEL WAS TRAINED and VALIDATED USING PNG FILES!!!" | |
| "</h3>" | |
| "</center>" | |
| "<p>" | |
| "<b>""<a href='https://www.kaggle.com/datasets/anasmohammedtahir/covidqu'>The model is trained using COVID-QU-Ex dataset</a>""</b>" | |
| " that the researchers from Qatar University compiled. THe Dataset consists of 33,920 chest X-ray (CXR) images:" | |
| "</p>" | |
| "<ul>" | |
| "<li>" | |
| "11,956 COVID-19" | |
| "</li>" | |
| "<li>" | |
| "11,263 Non-COVID infections (Viral or Bacterial Pneumonia)" | |
| "</li>" | |
| "<li>" | |
| "10,701 Normal" | |
| "</li>" | |
| "</ul>" | |
| "<p>" | |
| "Thanks to Kaggle & KaggleX, this is the largest ever created lung xray dataset, that I am aware of, publicly available as of October 2023." | |
| "</p>" | |
| "</body>" | |
| ) | |
| description = head | |
| examples = [ | |
| ['covid/covid_1038.png'], ['covid/covid_1034.png'], | |
| ['covid/cd.png'], ['covid/covid_1021.png'], | |
| ['covid/covid_1027.png'], ['covid/covid_1042.png'], | |
| ['covid/covid_1031.png'] | |
| ] | |
| #learn = load_learner('model/predictcovidfastaifinal18102023.pkl') | |
| learn = load_learner('model/final_20102023_eb7_model.pkl') | |
| categories = learn.dls.vocab | |
| def predict_image(get_image): | |
| pred, idx, probs = learn.predict(get_image) | |
| return dict(zip(categories, map(float, probs))) | |
| interpretation= 'shap' | |
| enable_queue=True | |
| gr.Interface(fn=predict_image, inputs=gr.Image(shape=(224,224)), | |
| outputs = gr.Label(num_top_classes=3),title=title,description=description,examples=examples, interpretation=interpretation,enable_queue=enable_queue).launch(share=False) | |