Uploading requirements.txt, app.py, model.py, class_names.txt, and 09_pretrained_vit_feature_extractor_food101_20_percent.pth

09_pretrained_vit_feature_extractor_food101_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8be7ecdce20b9c8f788e201fa32d9536f6d033e4ccaaa6204cf98f9e587c16
+size 343571601

app.py

@@ -0,0 +1,68 @@
+### 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
+
+# Set up class names
+with open("class_names.txt", "r") as f:
+    class_names = [food_name.strip() for food_name in f.readlines()]
+
+### 2. Model and transforms preparation ###
+# Create mode and transforms
+vit, vit_transforms = create_vit_model(num_classes = 101)
+
+# Load saved weights
+vit.load_state_dict(
+    torch.load(f = "09_pretrained_vit_feature_extractor_food101_20_percent.pth",
+               map_location = torch.device("cpu")) # load to CPU
+)
+
+### 3. Predict function ###
+def predict(img) -> Tuple[Dict, float]:
+    # Start a timer
+    start_time = timer()
+
+    # Transform the input image for use with ViT
+    img = vit_transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index
+
+    # Put model into eval mode, make prediction
+    vit.eval()
+    with torch.inference_mode():
+        # Pass transformed image through the model and turn the prediction logits into probabilities
+        pred_probs = torch.softmax(vit(img), dim = 1)
+
+    # Create a prediction label and prediction probability dictionary
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+    # Calculate pred time
+    end_time = timer()
+    pred_time = round(end_time - start_time, 4)
+
+    # Return pred dict and pred time
+    return pred_labels_and_probs, pred_time
+
+### 4. Gradio app ###
+# Create title, description, and article
+title = "Big Food Image Classifier 🍔👁️💪"
+description = "A [ViT transformer feature extractor](https://docs.pytorch.org/vision/main/models/generated/torchvision.models.vit_b_16.html#vit-b-16) computer vision model to classify [101 classes](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt) of food images (from Food101 dataset)."
+article = "Created at [turtlemb's GitHub](https://github.com/turtlemb)."
+
+# Create example list
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo = gr.Interface(fn = predict, # maps inputs to outputs
+                    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 demo
+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 +1,23 @@
+
+import torch
+import torchvision
+
+from torch import nn
+
+def create_vit_model(num_classes: int = 3,
+                     seed: int = 42):
+    # Create ViT_B_16 pre-trained 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 of the base layers
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head to suit our needs
+    torch.manual_seed(seed)
+    model.heads = nn.Sequential(nn.Linear(in_features = 768,
+                                          out_features = num_classes))
+
+    return model, transforms

requirements.txt

@@ -0,0 +1,2 @@
+torch==2.7.1
+torchvision==0.22.1