App init

09_pretrained_vit_feature_extractor_foodvision101.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e0d245cb68f96c0437ab697c24c2e30f883c9e6282a9be1f6e2752f59d583c
+size 343572169

app.py

@@ -0,0 +1,81 @@
+### 1. Imports and class names setup ### 
+import gradio as gr
+import os
+import torch
+
+from model import create_vit_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+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
+vit_food101, vit_transforms = create_vit_model(
+    num_classes=len(class_names),
+)
+
+# Load saved weights
+vit_food101.load_state_dict(
+    torch.load(
+        f="09_pretrained_vit_feature_extractor_foodvision101.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 = vit_transforms(img).unsqueeze(0)
+    
+    # Put model into evaluation mode and turn on inference mode
+    vit_food101.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(vit_food101(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 Vision Transformer 🥩👀🤖"
+description = "An ViT 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 = "Tested accuracy 77 %"
+
+# 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"),
+    outputs=[
+        gr.Label(num_top_classes=5, label="Predictions"),
+        gr.Number(label="Prediction time (s)"),
+    ],
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article,
+)
+
+# Launch the app!
+demo.launch()

class_names.txt

@@ -0,0 +1,101 @@
+apple_pie
+baby_back_ribs
+baklava
+beef_carpaccio
+beef_tartare
+beet_salad
+beignets
+bibimbap
+bread_pudding
+breakfast_burrito
+bruschetta
+caesar_salad
+cannoli
+caprese_salad
+carrot_cake
+ceviche
+cheese_plate
+cheesecake
+chicken_curry
+chicken_quesadilla
+chicken_wings
+chocolate_cake
+chocolate_mousse
+churros
+clam_chowder
+club_sandwich
+crab_cakes
+creme_brulee
+croque_madame
+cup_cakes
+deviled_eggs
+donuts
+dumplings
+edamame
+eggs_benedict
+escargots
+falafel
+filet_mignon
+fish_and_chips
+foie_gras
+french_fries
+french_onion_soup
+french_toast
+fried_calamari
+fried_rice
+frozen_yogurt
+garlic_bread
+gnocchi
+greek_salad
+grilled_cheese_sandwich
+grilled_salmon
+guacamole
+gyoza
+hamburger
+hot_and_sour_soup
+hot_dog
+huevos_rancheros
+hummus
+ice_cream
+lasagna
+lobster_bisque
+lobster_roll_sandwich
+macaroni_and_cheese
+macarons
+miso_soup
+mussels
+nachos
+omelette
+onion_rings
+oysters
+pad_thai
+paella
+pancakes
+panna_cotta
+peking_duck
+pho
+pizza
+pork_chop
+poutine
+prime_rib
+pulled_pork_sandwich
+ramen
+ravioli
+red_velvet_cake
+risotto
+samosa
+sashimi
+scallops
+seaweed_salad
+shrimp_and_grits
+spaghetti_bolognese
+spaghetti_carbonara
+spring_rolls
+steak
+strawberry_shortcake
+sushi
+tacos
+takoyaki
+tiramisu
+tuna_tartare
+waffles

model.py

@@ -0,0 +1,33 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_vit_model(num_classes:int=3, 
+                     seed:int=42):
+    """Creates a ViT-B/16 feature extractor model and transforms.
+
+    Args:
+        num_classes (int, optional): number of target classes. Defaults to 3.
+        seed (int, optional): random seed value for output layer. Defaults to 42.
+
+    Returns:
+        model (torch.nn.Module): ViT-B/16 feature extractor model. 
+        transforms (torchvision.transforms): ViT-B/16 image transforms.
+    """
+    # Create ViT_B_16 pretrained weights, transforms and model
+    weights = torchvision.models.ViT_B_16_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.vit_b_16(weights=weights)
+
+    # Freeze all layers in model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head to suit our needs (this will be trainable)
+    torch.manual_seed(seed)
+    model.heads = nn.Sequential(nn.Linear(in_features=768, # keep this the same as original model
+                                          out_features=num_classes)) # update to reflect target number of classes
+    
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch
+torchvision
+gradio