Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
----
-license: mit
----
+
+---
+license: apache-2.0
+tags:
+- image-classification
+- medical-imaging
+- cervical-cancer
+- pap-smear
+- pytorch
+---
+
+# AlexNet Fine-Tuned on HERLEV Dataset
+
+This repository provides a fine-tuned AlexNet model trained on the HERLEV cervical cytology dataset for multi-class cervical cell classification.
+
+## Model Details
+- Architecture: AlexNet
+- Framework: PyTorch
+- Input size: 224x224 RGB
+- Classes: 5
+
+## Classes
+0: Superficial–Intermediate  
+1: Parabasal  
+2: Koilocytotic  
+3: Dyskeratotic  
+4: Metaplastic  
+
+## How to Use
+
+```python
+import torch
+from PIL import Image
+from torchvision import transforms
+from model import load_model
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = load_model("best_alexnet.pth", device=device)
+
+transform = transforms.Compose([
+    transforms.Resize((224,224)),
+    transforms.ToTensor(),
+    transforms.Normalize(
+        mean=[0.485, 0.456, 0.406],
+        std=[0.229, 0.224, 0.225]
+    )
+])
+
+img = Image.open("cell_image.jpg").convert("RGB")
+img = transform(img).unsqueeze(0).to(device)
+
+with torch.no_grad():
+    pred = model(img).argmax(1)
+
+print("Prediction:", pred.item())
+
+Intended Use
+
+Research and educational purposes only.

best_alexnet.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3ac117fa20de155592a4c0198217da29ce74368f163fe7de961cfc0a7ea830
+size 227540992

config.json

@@ -0,0 +1,13 @@
+{
+    "architecture": "AlexNet",
+    "framework": "PyTorch",
+    "task": "Image Classification",
+    "domain": "Medical Imaging",
+    "dataset": "HERLEV",
+    "input_size": [
+        224,
+        224
+    ],
+    "num_classes": 5,
+    "finetuned": true
+}

labels.json

@@ -0,0 +1,7 @@
+{
+    "0": "Superficial-Intermediate",
+    "1": "Parabasal",
+    "2": "Koilocytotic",
+    "3": "Dyskeratotic",
+    "4": "Metaplastic"
+}

model.py

@@ -0,0 +1,15 @@
+
+import torch
+import torch.nn as nn
+from torchvision import models
+
+def load_model(model_path, num_classes=5, device="cpu"):
+    model = models.alexnet(weights=None)
+    model.classifier[6] = nn.Linear(4096, num_classes)
+
+    state_dict = torch.load(model_path, map_location=device)
+    model.load_state_dict(state_dict)
+
+    model.eval()
+    model.to(device)
+    return model

requirements.txt

@@ -0,0 +1,4 @@
+torch
+torchvision
+Pillow
+numpy