update files

.gitattributes

@@ -29,3 +29,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth filter=lfs diff=lfs merge=lfs -text
+*/*.jpg filter=lfs diff=lfs merge=lfs -text
+examples/04-pizza-dad.jpg filter=lfs diff=lfs merge=lfs -text

09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17e6a96bd4b62bf806ca8d41c3d47063079079201c7607b2d71ce672b3da321
+oid sha256:8c834646453534d566a227d53c28ec4a6fc7a956b546c77c3e13f305de7f8e5d
 size 31825353

app.py

@@ -1,16 +1,21 @@
+### 1. Imports and class names setup ### 
 import gradio as gr
+import os
 import torch
 
 from model import create_effnetb2_model
 from timeit import default_timer as timer
+from typing import Tuple, Dict
 
 # Setup class names
-with open("class_names.txt", "r") as f:
+with open("class_names.txt", "r") as f: # reading them in from class_names.txt
     class_names = [food_name.strip() for food_name in  f.readlines()]
+    
+### 2. Model and transforms preparation ###    
 
 # Create model
 model, transforms = create_effnetb2_model(
-    num_classes=101,
+    num_classes=101, # could also use len(class_names)
 )
 
 # Load saved weights
@@ -21,26 +26,44 @@ model.load_state_dict(
     )
 )
 
-# Create prediction code
-def predict(img):
+### 3. Predict function ###
+
+# 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()
-    img = transforms(img).unsqueeze(0)
-    model.eval()
+    
+    # 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():
-        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))
-    }
+        # 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 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 ###
 
-# Create Gradio app
+# Create title, description and article strings
 title = "FoodVision Big 🍔👁"
-description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into 101 different classes."
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into [101 different classes](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt)."
 article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
-example_dir = "demos/foodvision_big/examples"
 
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create Gradio interface 
 demo = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="pil"),
@@ -48,11 +71,11 @@ demo = gr.Interface(
         gr.Label(num_top_classes=5, label="Predictions"),
         gr.Number(label="Prediction time (s)"),
     ],
-    # examples="demo/foodvision_mini/examples",
-    interpretation="default",
+    examples=example_list,
     title=title,
     description=description,
     article=article,
 )
 
-demo.launch()
+# Launch the app!
+demo.launch()

model.py

@@ -1,20 +1,36 @@
+import torch
 import torchvision
 
 from torch import nn
 
 
-def create_effnetb2_model(num_classes: int):
+def create_effnetb2_model(num_classes:int=3, 
+                          seed:int=42):
+    """Creates an EfficientNetB2 feature extractor model and transforms.
+
+    Args:
+        num_classes (int, optional): number of classes in the classifier head. 
+            Defaults to 3.
+        seed (int, optional): random seed value. Defaults to 42.
+
+    Returns:
+        model (torch.nn.Module): EffNetB2 feature extractor model. 
+        transforms (torchvision.transforms): EffNetB2 image transforms.
+    """
+    # Create EffNetB2 pretrained weights, transforms and model
     weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
     transforms = weights.transforms()
     model = torchvision.models.efficientnet_b2(weights=weights)
 
-    # Freeze base model
+    # Freeze all layers in base model
     for param in model.parameters():
         param.requires_grad = False
 
-    # Change classifier head
+    # Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
     model.classifier = nn.Sequential(
         nn.Dropout(p=0.3, inplace=True),
         nn.Linear(in_features=1408, out_features=num_classes),
     )
-    return model, transforms
+    
+    return model, transforms

requirements.txt

@@ -1,3 +1,3 @@
 torch==1.12.0
 torchvision==0.13.0
-gradio==3.1.4
+gradio==3.1.4