Upload 5 files

Uploading required files

EffnetB2_Big_Label_Smoothning_14_Epochs.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e488619dcc465fba7722de99a6e559b4876389be7dc696e2e9ed7e2d0d6d2f5a
+size 31927482

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import os
+import torch
+from model import create_effnetb2
+from PIL import Image
+from pathlib import Path
+from timeit import default_timer as timer
+
+model, transforms = create_effnetb2(101)
+model = torch.load("EffnetB2_Big_Label_Smoothning_14_Epochs.pt")
+examples_path = [["examples/" + example] for example in os.listdir("examples")]
+
+with open("class_names.txt", 'r') as f:
+    food101_class_names_loaded = [food.strip() for food in f.readlines()]
+    f.close()
+
+def predict(img, model= model, transforms= transforms, class_names= food101_class_names_loaded, device= 'cpu'):
+    pred_labels_and_probs = {}
+    with torch.inference_mode():
+        model.eval()
+        model = model.to(device)
+        start_time = timer()
+        
+        transformed_img = transforms(img)
+        y_pred_probs = torch.softmax(model(transformed_img.unsqueeze(dim= 0)), dim= 1)
+        y_pred_class = class_names[torch.argmax(y_pred_probs, dim= 1)]
+        for i in range(len(class_names)):
+            pred_labels_and_probs[class_names[i]] = y_pred_probs[0][i].item()
+        
+        end_time = timer()
+        pred_time = round(end_time - start_time, 4)
+    return (pred_labels_and_probs, pred_time)
+
+
+
+title = "Food Vision Big"
+description = "An EfficientNetB2 feature extractor to classify food images into 101 classes from the Food101 dataset"
+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)")], title= title, 
+                    description= description, examples= examples_path)
+
+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 +1,25 @@
+import torch
+import torchvision
+from torchvision import models
+from torch import nn
+
+device = 'cpu'
+def create_effnetb2(num_output_classes: int):
+    """
+    Returns an effnetb2 feature extractor model with all layers except classifier layer frozen and the corresponding transforms for data preprocessing
+    
+    Args
+        num_output_classes (int) : The number of classes in the classifier head
+    """
+    effnet_b2_weights = models.EfficientNet_B2_Weights.DEFAULT
+    effnet_b2 = models.efficientnet_b2(weights= effnet_b2_weights).to(device)
+    effnet_transforms = effnet_b2_weights.transforms()
+    for params in effnet_b2.parameters():
+        params.requires_grad = False
+    
+    effnet_b2.classifier = nn.Sequential(
+    nn.Dropout(p= 0.3, inplace= True),
+    nn.Linear(in_features= 1408, out_features= num_output_classes, bias= True)
+    ).to(device)
+    
+    return effnet_b2, effnet_transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.3.0
+gradio==4.37.0
+torchvision==0.18.0