Add working ViT food classifier Space

app.py

@@ -0,0 +1,66 @@
+### 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
+class_names = ["apple_pie", "baby_back_ribs", "baklava", "beef_carpaccio", "beef_tartare", "beet_salad", "beignets", "bibimbap", "biryani", "bread_pudding", "breakfast_burrito", "bruschetta", "caesar_salad", "cannoli", "caprese_salad", "carrot_cake", "ceviche", "chai", "chapati", "cheese_plate", "cheesecake", "chicken_curry", "chicken_quesadilla", "chicken_wings", "chocolate_cake", "chocolate_mousse", "chole_bhature", "churros", "clam_chowder", "club_sandwich", "crab_cakes", "creme_brulee", "croque_madame", "cup_cakes", "dabeli", "dal", "deviled_eggs", "dhokla", "donuts", "dosa", "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", "idli", "jalebi", "kathi_rolls", "kofta", "kulfi", "lasagna", "lobster_bisque", "lobster_roll_sandwich", "macaroni_and_cheese", "macarons", "miso_soup", "momos", "mussels", "naan", "nachos", "omelette", "onion_rings", "oysters", "pad_thai", "paella", "pakoda", "pancakes", "pani_puri", "panna_cotta", "panner_butter_masala", "pav_bhaji", "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", "vadapav", "waffles"]
+vit, vit_transforms = create_vit_model(
+    num_classes=121, # len(class_names) would also work
+)
+vit.load_state_dict(
+    torch.load(
+        f="vit_epoch_2.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+# 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.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(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 = "VisionBite 🍕🥩🍣"
+description = "A Vision Transformer (ViT-Base-16) model trained to classify images of food into 121 distinct categories. The model uses a transformer-based architecture to extract visual features and achieve accurate classification across diverse food items."
+article = "Model Has been trained on Food121 dataset("https://huggingface.co/datasets/ItsNotRohit/Food121") and has an accuracy of 95% on top 5 predictions."
+
+# 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=121, 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()

model.py

@@ -0,0 +1,34 @@
+import torch
+import torchvision
+
+from torch import nn
+def create_vit_model(num_classes:int=121,
+                     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.LayerNorm(768),
+    nn.Dropout(0.2),  # Try 0.1 or 0.2
+    nn.Linear(768, 121)
+     )
+
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4

vit_epoch_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2feb708f66db4d26e017d955e6e8f8e64842e9a71e67e81cd3f4dc3f956eff
+size 343634614