Upload 3 files

app.py

@@ -0,0 +1,36 @@
+import gradio as gr
+from PIL import Image
+from model import load_model
+from torchvision import transforms
+import torch
+
+# Load your model
+model = load_model('best_model_augmented.pth')
+
+# Define the transformations for input images
+transform = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+])
+
+# Define the class labels
+class_names = ['Normal', 'Monkeypox', 'Chickenpox', 'Measles']
+
+def predict(image):
+    # Preprocess the image
+    image = transform(image).unsqueeze(0)  # Add batch dimension
+    with torch.no_grad():
+        outputs = model(image)
+        _, predicted = torch.max(outputs, 1)
+        return class_names[predicted.item()]
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.inputs.Image(type="pil", label="Upload an Image"),
+    outputs=gr.outputs.Label(num_top_classes=4, label="Prediction"),
+    live=True
+)
+
+# Launch the interface
+iface.launch()

best_model_augmented.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ac0ac82eec1d104340ac30eea19ecf22ff94d283a8fa0631298567d7a738bca
+size 84782380

model.py

@@ -0,0 +1,34 @@
+import torch
+import torch.nn as nn
+from torchvision import models
+import torch.nn.functional as F
+
+class CustomModel(nn.Module):
+    def __init__(self, num_classes=4):
+        super(CustomModel, self).__init__()
+        self.efficientnet = models.efficientnet_v2_s(weights=models.EfficientNet_V2_S_Weights.IMAGENET1K_V1)
+        num_features = self.efficientnet.classifier[1].in_features
+        self.efficientnet = nn.Sequential(*list(self.efficientnet.children())[:-1])
+        self.gap = nn.AdaptiveAvgPool2d(1)
+        self.fc1 = nn.Linear(num_features, 512)
+        self.dropout1 = nn.Dropout(0.5)
+        self.fc2 = nn.Linear(512, 256)
+        self.dropout2 = nn.Dropout(0.3)
+        self.fc3 = nn.Linear(256, num_classes)
+
+    def forward(self, x):
+        x = self.efficientnet(x)
+        x = self.gap(x)
+        x = torch.flatten(x, 1)
+        x = F.relu(self.fc1(x))
+        x = self.dropout1(x)
+        x = F.relu(self.fc2(x))
+        x = self.dropout2(x)
+        x = self.fc3(x)
+        return x
+
+def load_model(model_path):
+    model = CustomModel()
+    model.load_state_dict(torch.load(model_path))
+    model.eval()
+    return model