Upload 8 files

mri_classifier/app.py

@@ -0,0 +1,64 @@
+
+import gradio as gr
+import os
+import torch
+
+from model import create_efficientb2_model
+from timeit import default_timer as timer
+
+class_names = [
+    "glioma",
+    "meningioma",
+    "notumor",
+    "pituitary"
+]
+
+efficientb2, transforms = create_efficientb2_model(num_classes=4)
+
+efficientb2.load_state_dict(
+    torch.load(
+        f="efficientnet_mri_model.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
+def predict_img(img):
+
+  start_time = timer()
+
+  img = transforms(img).unsqueeze(0)
+
+  efficientb2.eval()
+
+  with torch.inference_mode():
+
+    pred_probs = torch.softmax(efficientb2(img), dim=1)
+
+    pred_labels_and_probs = {
+        class_names[i] : float(pred_probs[0][i]) for i in range(len(class_names))
+    }
+
+    pred_time = round(timer() - start_time(),5)
+
+    return pred_labels_and_probs, pred_time
+
+title = "MRI Result Finder"
+description = "Efficientnet b2 model to classify MRI images"
+article = "Created at 2026"
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+demo = gr.Interface(
+    fn=predict_img,
+    outputs=[
+        gr.Label(num_top_classes=4,label="Predictions"),
+        gr.Number(label="Prediction Time")
+    ],
+    examples = example_list,
+    title = title,
+    description = description,
+    article = article
+)
+
+
+demo.lunch()

mri_classifier/efficientnet_mri_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2dfe58e56a2b31937368faa189edbe42305f03760359665151389141c78380
+size 31365477

mri_classifier/model.py

@@ -0,0 +1,23 @@
+
+import torch
+import torchvision
+
+from torch import nn
+
+def create_efficientb2_model(
+    num_classes: int=4,
+    seed: int=42):
+  
+  weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+  model = torchvision.models.efficientnet_b2(weights=weights)
+  auto_transform = weights.transforms()
+
+  for params in model.parameters():
+    params.requires_grad = False
+  
+  model.classifier = nn.Sequential(
+      nn.Dropout(p=0.3,inplace=True),
+      nn.Linear(1408,num_classes)
+  )
+
+  return model, auto_transform

mri_classifier/requirements.txt

@@ -0,0 +1,4 @@
+
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4