Upload 6 files

09_pretrained_effnetb2_feature_extractor_food101.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caaf88c75aa28508d3f2cf137694a04be219a7e2ad54dceb85c329bd8e5fcb55
+size 31851002

app.py

@@ -0,0 +1,71 @@
+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
+foodvision101_class_names_path = "class_names.txt"
+with open(foodvision101_class_names_path, "r") as f:
+  class_names = [food.strip() for food in f.readlines()]
+
+# Model and transforms
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=101)
+
+# Load save weights
+effnetb2.load_state_dict(
+    torch.load(
+        f="09_pretrained_effnetb2_feature_extractor_food101.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
+# Predict function
+def predict(img) -> Tuple[Dict, float]:
+  # Start a timer
+  start_time = timer()
+
+  # Transform the input image for use with EffNetB2
+  img = effnetb2_transforms(img).unsqueeze(0)
+
+  # Put model into eval mode, make prediction
+  effnetb2.eval()
+  with torch.inference_mode():
+    # Pass transformed image through the model
+    pred_probs = torch.softmax(effnetb2(img), dim=1)
+
+  # Create 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
+
+# Gradio app
+# Create title, description and article
+title = "FoodVision 101 Learning Practice"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images"
+article = "Created at PyTorch Model Deployment"
+
+# Create example list
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo= gr.Interface(fn=predict,
+                   inputs=gr.Image(type="pil"),
+                   outputs=[gr.Label(num_top_classes=3, label="Predicitons"),
+                            gr.Number(label="Prediction Time (s)")],
+                   examples=example_list,
+                   title=title,
+                   description=description,
+                   article=article)
+
+# Launching 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 +1,49 @@
+import torch
+import torchvision
+from torchvision.models import efficientnet_b2, EfficientNet_B2_Weights
+from torchvision.models._api import WeightsEnum
+from torch.hub import load_state_dict_from_url
+
+from torch import nn
+
+def get_state_dict(self, *args, **kwargs):
+        kwargs.pop("check_hash")
+        return load_state_dict_from_url(self.url, *args, **kwargs)
+        
+def create_effnetb2_model(num_classes:int=3, 
+                          seed:int=42):
+    """Creates an EfficientNetB2 feature extractor model and transforms.
+
+    Args:
+        num_classes (int, optional): number of classes in the classifier head. 
+            Defaults to 3.
+        seed (int, optional): random seed value. Defaults to 42.
+
+    Returns:
+        model (torch.nn.Module): EffNetB2 feature extractor model. 
+        transforms (torchvision.transforms): EffNetB2 image transforms.
+    """
+    # Create EffNetB2 pretrained weights, transforms and model
+    
+
+    
+    WeightsEnum.get_state_dict = get_state_dict
+
+    efficientnet_b2(weights=EfficientNet_B2_Weights.DEFAULT)
+
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = efficientnet_b2(weights=weights)
+
+    # Freeze all layers in base model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes),
+    )
+    
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.1.0
+torchvision==0.16.0
+gradio==3.45.0