initial commit

VIT_32_20_003.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9cc08c3955685db4bc561ab448906e0a738e58b6c199a652bea705824cb35f
+size 343564394

app.py

@@ -0,0 +1,59 @@
+### 1. Imports and class names setup ### 
+import gradio as gr
+import os
+import torch
+
+from model import createVITModel
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+with open("classes.txt", "r") as f: # reading them in from class_names.txt
+    class_names = [food_name.strip() for food_name in  f.readlines()]
+
+model, vit_transform = createVITModel()
+model.load_state_dict(torch.load('VIT_32_20_003.pth'))
+model = model.to('cpu')
+
+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_transform(img).unsqueeze(dim=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(model(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
+
+
+# Create title, description and article strings
+title = "Food Image Classifier 🍰 🎂"
+description = "A VIT Food Classifier."
+article = ""
+
+# 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=5, label="Predictions"), # what are the outputs?
+                             gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
+                    examples=example_list, 
+                    title=title,
+                    description=description,
+                    article=article)
+
+# Launch the demo!
+demo.launch(debug=False) # generate a publically shareable URL?

classes.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 +1,16 @@
+import torch
+import torch.nn as nn
+import torchvision
+
+def createVITModel(out_features: int) -> nn.Module:
+    # 1. Get pretrained weights for ViT-Base
+    pretrained_vit_weights = torchvision.models.ViT_B_16_Weights.DEFAULT
+    # 2. Setup a ViT model instance with pretrained weights
+    pretrained_vit = torchvision.models.vit_b_16(weights=pretrained_vit_weights)
+    # 3. Freeze the base parameters
+    for parameter in pretrained_vit.parameters():
+        parameter.requires_grad = False
+    # 4. Change the classifier head (set the seeds to ensure same initialization with linear head)
+    pretrained_vit.heads = nn.Linear(in_features=768, out_features=out_features).to('cpu')
+    vit_transforms = pretrained_vit_weights.transforms()
+    return pretrained_vit, vit_transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.1.2
+torchvision==0.16.2
+gradio==4.24.0