DenseNet121 Chest Xray Classifier

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/NORMAL(1283).jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,77 @@
+### 1. Imports and class names setup ###
+import gradio as gr
+import os
+import torch
+
+from model import create_densenet121_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+class_names = ["COVID19", "NORMAL", "PNEUMONIA"]
+
+### 2. Model and transforms preparation ###
+
+# Create DenseNet121 model
+densenet121, densenet121_transforms = create_densenet121_model(
+    num_classes=3, # len(class_names) would also work
+)
+
+# Load saved weights
+densenet121.load_state_dict(
+    torch.load(
+        f="densenet_chest_xray_weight.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+### 3. Predict function ###
+
+# Create predict function
+def predict(img) -> Tuple[Dict, float]:
+    """Transforms and performs a prediction on img and returns prediction and time taken.
+    """
+    # Start the timer
+    start_time = timer()
+
+    # Transform the target image and add a batch dimension
+    img = densenet121_transforms(img).unsqueeze(0)
+
+    # Put model into evaluation mode and turn on inference mode
+    effnetb2.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+
+    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+    # Calculate the prediction time
+    pred_time = round(timer() - start_time, 5)
+
+    # Return the prediction dictionary and prediction time
+    return pred_labels_and_probs, pred_time
+
+### 4. Gradio app ###
+
+# Create title, description and article strings
+title = "Chest X-ray Analysis for COVID-19, Pneumonia, and Normal Cases using DenseNet121"
+description = "Utilizing Deep Learning for accurate detection and classification of Chest X-ray images."
+article = "This project employs the DenseNet121 model to analyze Chest X-ray images for classification into COVID-19, Pneumonia, and Normal cases. Leveraging the capabilities of Deep Learning, the model ensures precise and reliable results, contributing to improved medical diagnostics."
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo = gr.Interface(fn=predict, # mapping function from input to output
+                    inputs=gr.Image(type="pil"), # what are the inputs?
+                    outputs=[gr.Label(num_top_classes=3, label="Predictions"), # what are the outputs?
+                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
+                    # Create examples list from "examples/" directory
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article)
+
+# Launch the demo!
+demo.launch()

densenet_chest_xray_weight.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e385bc0798f93345f9669ea6e5e80062b4147d680614b0725587088bcef5ca
+size 28446341

model.py

@@ -0,0 +1,27 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_densenet121_model(num_classes:int=3,
+                          seed:int=42):
+    # Create DenseNet121 pretrained weights, transforms and model
+    weights = torchvision.models.DenseNet121_Weights.DEFAULT 
+    transforms = weights.transforms()
+    model = torchvision.models.densenet121(weights=weights)
+
+    # Freeze all layers in base model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
+
+    model.classifier = torch.nn.Sequential(
+    torch.nn.Dropout(p=0.2, inplace=True),
+    torch.nn.Linear(in_features=1024,
+                    out_features=3,
+                    bias=True))
+
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4