Upload app.py

app.py

@@ -1,4 +1,4 @@
-### 1. Imports and class names setup
+### 1. Imports and class names setup ### 
 import gradio as gr
 import os
 import torch
@@ -8,62 +8,70 @@ from timeit import default_timer as timer
 from typing import Tuple, Dict
 
 # Setup class names
-class_names = ['pizza', 'steak', 'sushi']
+class_names = ["pizza", "steak", "sushi"]
 
-### 2. Model and transforms preparation
-effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=3)
+### 2. Model and transforms preparation ###
+
+# Create EffNetB2 model
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=3, # len(class_names) would also work
+)
 
 # Load saved weights
 effnetb2.load_state_dict(
     torch.load(
         f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth",
-        map_location=torch.device("cpu") # load the model to the CPU
+        map_location=torch.device("cpu"),  # load to CPU
     )
 )
-### Predict function
-
-def predict(img) -> Tuple[Dict, float]:
-  # Start a timer
-  start_time = timer()
 
-  # Transform the input image for use with EffNetB2
-  img = effnetb2_transforms(img).unsqueeze(0)  # unsqueeze = add batch dimension on 0th index.
+### 3. Predict function ###
 
-  # put model into eval mode, make predictions
-  effnetb2.eval()
-  with torch.inference_mode():
-    # Pass transformed image through model and turn the prediction logits into probabilities
-    pred_probs = torch.softmax(effnetb2(img), dim=1)
-
-    # Create a prediction label and prediction probability dictionary
+# Create predict function
+def predict(img) -> Tuple[Dict, float]:
+    """Transforms and performs a prediction on img and returns prediction and time taken.
+    """
+    # Start the timer
+    start_time = timer()
+    
+    # Transform the target image and add a batch dimension
+    img = effnetb2_transforms(img).unsqueeze(0)
+    
+    # Put model into evaluation mode and turn on inference mode
+    effnetb2.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+    
+    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
     pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
-
-    # Calculate pred time
-    end_time = timer()
-    pred_time = round(end_time - start_time, 4)
-
-    # Return pred dict and pred time
+    
+    # Calculate the prediction time
+    pred_time = round(timer() - start_time, 5)
+    
+    # Return the prediction dictionary and prediction time 
     return pred_labels_and_probs, pred_time
 
-## 4. Gradio app
+### 4. Gradio app ###
 
-# Create title, description and article.
+# Create title, description and article strings
 title = "FoodVision Mini 🍕🥩🍣"
-description = "An [EfficientNetB2 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) computer vision model to classify images as pizza, steak or sushi."
-article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/#74-building-a-gradio-interface)."
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
 
-# Create example list
-example_list = [["examples/" + example] for exmple in os.listdir("examples")]
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
 
 # Create the Gradio demo
-demo = gr.Interface(fn=predict,  # maps inputs to outputs
-                    inputs=gr.Image(type="pil"),
-                    outputs=[gr.Label(num_top_classes=3, label="Predictions"),
-                             gr.Number(label="Prediction time (s)")],
-                                    examples=example_list,
-                                    title=title,
-                                    description=description,
-                                    article=article)
+demo = gr.Interface(fn=predict, # mapping function from input to output
+                    inputs=gr.Image(type="pil"), # what are the inputs?
+                    outputs=[gr.Label(num_top_classes=3, label="Predictions"), # what are the outputs?
+                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
+                    # Create examples list from "examples/" directory
+                    examples=example_list, 
+                    title=title,
+                    description=description,
+                    article=article)
 
 # Launch the demo!
 demo.launch()