Foodvision app

.gitattributes

@@ -33,3 +33,4 @@ 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_pizza_steak_sushi_20_percent.pth filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+__pycache__/
+env/
+flagged/

app.py

@@ -0,0 +1,153 @@
+### 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
+class_names = ["pizza", "steak", "sushi"]
+
+### 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 to CPU
+    )
+)
+
+### 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()
+    
+    # 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 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 title, description and article strings
+title = "FoodVision Mini 🍕🥩🍣"
+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 examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+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()
+# 1. Imports and class name
+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 name
+class_names = ['pizza', 'steak', 'sushi']
+
+# 2. Model and transforms preparation
+
+# create effnetb2 model
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=3)
+
+# load saved weights
+effnetb2.load_state_dict(
+    torch.load(f='09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent',
+               map_location = torch.device('cpu')
+              )
+)
+
+# 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()
+
+    # transform the target img and add a batch dimension
+    img = effnetb2_transforms(img).unsqueeze(dim=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
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][1]) for i in range(len(class_names))}
+    
+    # end time
+    end_time = timer()
+
+    # calculate the prediction time
+    pred_time = round(end_time - start_time, 5)
+
+    return pred_labels_and_probs, pred_time
+
+# 4. Gradio App
+
+# Create titme, description, and article strings
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "Learned from [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
+
+# create examples list from 'examples/' directory
+example_list = [[f'examples/{example}'] for example in os.listdir('examples')]
+
+# Create the Gradio demo
+demo = gr.Interface(fn=predict,
+                    inputs=gr.Image(type='pil'),
+                    outputs=[gr.Label(num_top_classes=3, label='Prediction'),
+                            gr.Number(label='Prediction time(s)')],
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article)
+
+# launch the demo!
+demo.launch()

model.py

@@ -0,0 +1,35 @@
+import torch
+import torchvision
+
+from torch import nn
+
+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 all the layers in the base model
+    for param in model.features.parameters():
+        param.requires_grad = False
+
+    # change the 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

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.2.2
+torchvision==0.17.2
+gradio==4.44.0