Upload app.py

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import torch
+
+from model import create_effnetb2_model
+from timeit import default_timer as timer
+
+# Setup class names
+with open("class_names.txt", "r") as f:
+    class_names = [food_name.strip() for food_name in  f.readlines()]
+
+# Create model
+model, transforms = create_effnetb2_model(
+    num_classes=101,
+)
+
+# Load saved weights
+model.load_state_dict(
+    torch.load(
+        f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+# Create prediction code
+def predict(img):
+    start_time = timer()
+    img = transforms(img).unsqueeze(0)
+    model.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(model(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
+
+
+# Create Gradio app
+title = "FoodVision Big 🍔👁"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into 101 different classes."
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
+
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Label(num_top_classes=5, label="Predictions"),
+        gr.Number(label="Prediction time (s)"),
+    ],
+    examples=[["examples/04-pizza-dad.jpeg"]],
+    interpretation="default",
+    title=title,
+    description=description,
+    article=article,
+)
+
+demo.launch()