Create app.py

app.py

@@ -0,0 +1,79 @@
+import torch
+import numpy as np
+from huggingface_hub import hf_hub_download
+from tiatoolbox.models.arch import resnet50
+from tiatoolbox.models.models_abc import ModelABC
+from torchvision import transforms
+from PIL import Image
+import gradio as gr
+
+
+# -------------------------------------------------
+# تحميل الموديل من Hugging Face
+# -------------------------------------------------
+
+MODEL_REPO = "kaczmarj/lymphnodes-tiatoolbox-resnet50.patchcamelyon"
+MODEL_FILE = "resnet50-pcam.pth"   # غيّره لو اسم الملف مختلف
+
+model_path = hf_hub_download(
+    repo_id=MODEL_REPO,
+    filename=MODEL_FILE
+)
+
+# -------------------------------------------------
+# إعداد موديل ResNet50 (TIAToolbox)
+# -------------------------------------------------
+
+class PCamModel(ModelABC):
+    def __init__(self):
+        super().__init__()
+        self.model = resnet50(pretrained=False, num_classes=2)
+        self.model.load_state_dict(torch.load(model_path, map_location="cpu"))
+        self.model.eval()
+
+    def forward(self, imgs):
+        return self.model(imgs)
+
+
+model = PCamModel()
+
+# -------------------------------------------------
+# التحويلات المطلوبة للصورة
+# -------------------------------------------------
+
+transform = transforms.Compose([
+    transforms.Resize((96, 96)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+])
+
+labels = ["No Tumor", "Tumor"]
+
+
+# -------------------------------------------------
+# دالة التنبؤ
+# -------------------------------------------------
+
+def predict(image):
+    img = transform(image).unsqueeze(0)
+
+    with torch.no_grad():
+        logits = model(img)[0]
+        probs = torch.softmax(logits, dim=0).numpy()
+
+    return {labels[0]: float(probs[0]), labels[1]: float(probs[1])}
+
+
+# -------------------------------------------------
+# واجهة Gradio
+# -------------------------------------------------
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Label(),
+    title="Lymph Node Tumor Detection (PatchCamelyon – ResNet50)",
+    description="Model: kaczmarj/lymphnodes-tiatoolbox-resnet50.patchcamelyon"
+)
+
+demo.launch()