first commit

app.py

@@ -0,0 +1,76 @@
+### 1. Imports and class names setup ### 
+import gradio as gr
+import os
+import torch
+
+from model import create_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
+model, transform = create_model(
+    'vit_base_patch16_224_miil_in21k',
+    num_classes=101, # could also use len(class_names)
+)
+
+# Load saved weights
+model.load_state_dict(
+    torch.load(
+        f="/content/drive/MyDrive/CS431-EndCourseProject/vit_b_16_food101_cifar100.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 = transform(img).unsqueeze(0)
+    
+    # Put model into evaluation mode and turn on inference mode
+    model.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 Big 🍔👁"
+description = "An fine-tuned Vision Transformer vision model to classify images of food into 101 different classes."
+
+# 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)"),
+    ],
+    title=title,
+    description=description,
+)
+
+# 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 +1,19 @@
+import torch
+import timm
+from torchvision import transforms
+
+def create_model(model_name, num_classes):
+  transform = transforms.Compose([
+      transforms.Resize((224, 224)),
+      transforms.CenterCrop(224),
+      transforms.ToTensor(),
+      transforms.Normalize(mean=[0.0, 0.0, 0.0], std=[1.0, 1.0, 1.0])
+  ])
+  
+  # Load the pretrained model
+  model = timm.create_model('vit_base_patch16_224_miil_in21k', pretrained=True)
+  model.head = torch.nn.Linear(768, num_classes)
+
+  for param in model.parameters():
+    param.requires_grad = True
+  return model, transform

requirements.txt

@@ -0,0 +1,4 @@
+torch==2.1.0
+torchvision==0.16.0
+timm==0.9.10
+gradio==4.3.0