Model to classify 101 food classes

app.py

@@ -0,0 +1,51 @@
+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
+
+with open("class_names.txt","r") as f:
+    class_names=[food_name.strip() for food_name in f.readlines()]
+
+effnetb2,effnetb2_transforms=create_effnetb2_model(num_classes=101)
+
+effnetb2.load_state_dict(
+    torch.load(
+        f="effnetb2_food101_large.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
+def predict(img)->Tuple[Dict,float]:
+    start_timer=timer()
+    img=effnetb2_transforms(img).unsqueeze(0)
+
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_prob=torch.softmax(effnetb2(img),dim=1)
+    pred_label_and_prob={class_names[i]:float(pred_prob[0][i]) for i in range(len(class_names))}
+    pred_time=round(timer()-start_timer,5)
+
+    return pred_label_and_prob,pred_time
+
+title="FoodVision Large"
+description="An EfficientNet B2 Feature extractor computer vision model to classify images of food consisting of 101 classes."
+article="Created on 22 Jan 2025"
+example_list=[["examples/"+example] for example in os.listdir("examples")]
+
+demo=gr.Interface(
+    fn=predict,
+    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
+)
+
+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

effnetb2_food101_large.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc169f160701ba93789f1dce7e81cde9d85f1a1140ffa724dec53c6847603d1a
+size 31834234

model.py

@@ -0,0 +1,19 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_effnetb2_model(num_classes:int=3,seed:int=42):
+    weights=torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms=weights.transforms()
+    model=torchvision.models.efficientnet_b2(weights=weights)
+
+    for param in model.parameters():
+        param.requires_grad=False
+
+    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==2.5.1
+torchvision==0.20.1
+gradio==5.12.0