we have unzipped and moved the files to the right directory

app.py

@@ -0,0 +1,75 @@
+# import the essentials
+import torch
+import torchvision
+import time
+import gradio as gr
+import numpy as np
+from pathlib import Path
+from model import create_effnet_b2_model
+
+with open(class_names.txt) as f:
+  class_names = [class_name.strip('\n') for class_name in f.readlines()]
+
+device = 'cuda' if torch.cuda.is_available else 'cpu'
+
+# creating the vit_b_16_model and loading it with state_dict of our trained model
+effnetb2_model,effnetb2_transform = create_effnet_b2_model(num_classes=len(class_names))
+effnetb2_model.load_state_dict(torch.load(f='effnetb2_20percent_101classes.pth'))
+
+# create the predict function
+def predict(img):
+
+  """
+  args:
+  img: is an image
+
+  returns: prediction class, prediction probability, and time taken to make the prediction
+
+  """
+
+  # transforming the image
+  tr_img = effnetb2_transform(img).unsqueeze(dim=0).to(device)
+
+  # make prediction with vit_b_16
+  model = effnetb2_model.to(device)
+
+  # starting the time
+  start_time = time.perf_counter()
+
+  model.eval()
+  with torch.inference_mode():
+    pred_logit = model(tr_img)
+    pred_label = torch.argmax(pred_logit,dim=1).cpu()
+    pred_prob = torch.max(torch.softmax(pred_logit,dim=1)).cpu().item()
+
+  # ending the time
+  end_time = time.perf_counter()
+  pred_prob  = float(np.round(pred_prob,3))
+  pred_class = class_names[pred_label]
+  time_taken = float(np.round(end_time-start_time,3))
+
+
+
+  return pred_class,pred_prob,time_taken
+
+
+# create example list
+example_dir = Path('demos/foodvision_big/examples')
+example_list = [['examples/' + str(filepath)] for filepath in os.listdir(example_dir)]
+
+# create Gradio interface
+description = 'A machine learning model to classify images into pizza,steak and sushi appropriately'
+title = 'Image Classifier'
+
+
+demo = gr.Interface(fn=predict, # this function maps the inputs to the output
+                    inputs=gr.Image(type='pil'), # pillow image
+                    outputs=[gr.Label(num_top_classes=1,label='Prediction'),
+                             gr.Number(label='prediction probability'),
+                             gr.Number(label='prediction time(s)')],
+                    examples=example_list,
+                    description=description,
+                    title=title
+                    )
+
+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_20percent_101classes.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0556fcf79356e837c2c4bb9531c9afb83154098d9fb8f5bcebd6151ede705f9
+size 31837882

model.py

@@ -0,0 +1,23 @@
+import torch
+import torchvision
+def create_effnet_b2_model(num_classes=101):
+  """
+  Args: num_classes is total number of classes
+
+  returns: model and its corresponding model_specific transform
+  """
+  weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+  transform = torchvision.models.EfficientNet_B2_Weights.DEFAULT.transforms()
+  model = torchvision.models.efficientnet_b2(weights=weights)
+
+  # freeze the parameters from training
+  for param in model.parameters():
+    param.requires_grad = False
+
+  # modifying the classifier layer
+  model.classifier = torch.nn.Sequential(
+      torch.nn.Dropout(p=0.3,inplace=True),
+      torch.nn.Linear(in_features=1408,out_features=num_classes)
+  )
+
+  return model,transform

requirements.txt

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