Upload 5 files

app.py

@@ -0,0 +1,42 @@
+import os
+from pathlib import Path
+import random
+import torch
+from model import create_effnetb2
+import gradio as gr
+from typing import Dict, Tuple
+from time import time
+
+effnetb2, effnetb2_transforms = create_effnetb2(101)
+effnetb2.load_state_dict(torch.load(f='effnetB2_101.pth', map_location=torch.device('cpu')))
+with open('class_names.txt', 'r') as f:
+    class_names = [food.strip() for food in f.readlines()]
+
+def predict(image) -> Tuple[Dict, float]:
+    start = time()
+    transformed_image = effnetb2_transforms(image).unsqueeze(0)
+    effnetb2.eval()
+    with torch.inference_mode():
+        y_logits = effnetb2(transformed_image)
+        probs = torch.softmax(y_logits, dim=1).squeeze()
+    pred_labels_and_probs = {class_names[i]: float(probs[i].item()) for i in range(len(class_names))}
+    end = time()
+    return pred_labels_and_probs, round(end - start, 5)
+
+images = os.listdir('examples')
+example_list = [[str('examples/' + x)] for x in images]
+# Create title, description and article strings
+title = "FoodVision"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food."
+
+# 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)
+
+# Launch the demo!
+demo.launch(debug=False)

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

effnetB2_101.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ac47e15babde6fa9b82e8b646937c3d392c71a203895db5a7bab561b322aa5
+size 31828666

model.py

@@ -0,0 +1,23 @@
+import torch
+import torchvision
+from torch import nn
+from torchvision.models._api import WeightsEnum
+from torch.hub import load_state_dict_from_url
+def get_state_dict(self, *args, **kwargs):
+    kwargs.pop("check_hash")
+    return load_state_dict_from_url(self.url, *args, **kwargs)
+WeightsEnum.get_state_dict = get_state_dict
+
+def create_effnetb2(num_classes: int=3):
+    effnetb2_weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    effnetb2_transforms = effnetb2_weights.transforms()
+    effnetb2 = torchvision.models.efficientnet_b2(weights="DEFAULT")
+    for param in effnetb2.parameters():
+        param.requires_grad = False
+    torch.manual_seed(42)
+    torch.cuda.manual_seed(42)
+    effnetb2.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes)
+    )
+    return effnetb2, effnetb2_transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.1.2
+torchvision==0.16.2
+gradio==4.15.0