Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/01-StreetStyle-Chicken-Biryani.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,67 @@
+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
+
+# Setup class names by reading them from the file
+with open(file="class_names.txt", mode='r') as f:
+    class_names = [food_name.strip() for food_name in f.readlines()]
+
+### Model and transforms preparation ###
+# Create model and transforms for EfficientNetB2
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=101)
+
+# Load saved weights into the model
+effnetb2.load_state_dict(
+    torch.load(f="effnetb2_feature_extractor_food101_20_percent.pth",
+               map_location=torch.device("cpu"))  # load model to CPU
+)
+
+### Predict function ###
+def predict(img) -> Tuple[Dict, float]:
+    # Start a timer
+    start_time = timer()
+
+    # Transform the input image for use with EfficientNetB2
+    img = effnetb2_transforms(img).unsqueeze(0)  # unsqueeze to add the batch dimension
+
+    # Put model into evaluation mode
+    effnetb2.eval()
+    with torch.inference_mode():
+        # Pass transformed image through the model and turn the prediction logits into probabilities
+        pred_probs = torch.softmax(input=effnetb2(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 prediction time
+    end_time = timer()
+    pred_time = round(end_time - start_time, 4)
+
+    # Return prediction dictionary and prediction time
+    return pred_labels_and_probs, pred_time
+
+### Gradio app ###
+# Create title, description, and article for the Gradio interface
+title = "Food101_Big_Classification"
+description = "An [EfficientNetB2 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) computer vision model to classify images [101 classes of food from the Food101 dataset](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt)."
+article = "Created at [https://github.com/MRameezU/Food101_Big_Classification_EffNetB2/blob/e9c502b4f9e5a0f68e102184d18a6b934334b17b/food101-big-classification-effnetb2.ipynb]"
+
+# Create a list of example images
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo interface
+demo = gr.Interface(fn=predict,  # function to map inputs to outputs
+                    inputs=gr.Image(type="pil"),  # input type is an image
+                    outputs=[gr.Label(num_top_classes=5, label="Predictions"),  # output top 5 predictions
+                             gr.Number(label="Prediction time (s)")],  # output prediction time
+                    examples=example_list,  # provide example images
+                    title=title,  # set the title of the interface
+                    description=description,  # set the description
+                    article=article)  # set the article link
+
+# Launch the Gradio 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 +1,38 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_effnetb2_model(num_classes: int = 3, seed: int = 42):
+    """
+    Creates an EfficientNetB2 model with a custom classifier for the given number of classes.
+
+    Args:
+    num_classes (int): Number of output classes for the classifier.
+    seed (int): Random seed for reproducibility.
+
+    Returns:
+    model (torchvision.models): Modified EfficientNetB2 model with custom classifier.
+    transforms (torchvision.transforms): Preprocessing transforms for the model.
+    """
+    # Load pre-trained EfficientNetB2 weights and transforms
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+
+    # Initialize the EfficientNetB2 model with pre-trained weights
+    model = torchvision.models.efficientnet_b2(weights=weights)
+
+    # Freeze the base parameters of the model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Set the random seed for reproducibility
+    torch.manual_seed(seed)
+
+    # Replace the classifier with a custom one for the specified number of classes
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),  # Add dropout for regularization
+        nn.Linear(in_features=1408, out_features=num_classes)  # Linear layer for classification
+    )
+
+    return model, transforms

requirements.txt

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