Create app.py

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import numpy as np
+from PIL import Image, ImageDraw
+from huggingface_hub import hf_hub_download
+# carica SAM e GroundingDINO direttamente dall’HF Hub
+SAM_CHECKPOINT = hf_hub_download("facebook/sam-vit-base", "sam_vit_b.pth")
+GDINO_CONFIG    = hf_hub_download("IDEA-Research/GroundingDINO", "GroundingDINO_SwinT_OGC.py")
+GDINO_CHECKPT   = hf_hub_download("IDEA-Research/GroundingDINO", "groundingdino_swint_ogc.pth")
+
+# — pseudocodice di import —
+from segment_anything import sam_model
+from groundingdino.util.inference import load_model, predict
+
+sam    = sam_model.load_from_checkpoint(SAM_CHECKPOINT)
+gdino  = load_model(GDINO_CONFIG, GDINO_CHECKPT)
+
+def recognize(img, prompt, conf):
+    masks = sam.segment(img)       # 1. segmentazione zero‑shot
+    out   = Image.fromarray(img).convert("RGBA")
+    draw  = ImageDraw.Draw(out, "RGBA")
+    results = []
+    for m in masks:
+        label, score = predict(gdino, img, m, prompt)  # 2. classificazione zero‑shot
+        if score<conf: continue
+        yy, xx = np.where(m)
+        bbox = (xx.min(), yy.min(), xx.max(), yy.max())
+        area = int(m.sum())
+        draw.rectangle(bbox, outline=(255,0,0,180), width=3)
+        draw.text((bbox[0], bbox[1]-10), f"{label} {score:.2f}", fill=(255,0,0,180))
+        results.append({"label":label, "score":score, "area":area, "bbox":bbox})
+    return np.array(out), results
+
+app = gr.Interface(
+    fn=recognize,
+    inputs=[
+      gr.Image(type="numpy", label="Upload Image"),
+      gr.Textbox(label="Prompt (comma‑separated)"),
+      gr.Slider(0,1,0.25, label="Confidence Threshold"),
+    ],
+    outputs=[
+      gr.Image(label="Overlay"),
+      gr.JSON(label="Detections")
+    ],
+    title="Zero‑Shot Component Recognition",
+    description="Segmenta e classifica componenti meccanici da foto, senza training specifico."
+)
+
+if __name__=="__main__":
+    app.launch()