Initial commit

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+example/04-pizza-dad.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,73 @@
+
+# Import and class names setup
+import gradio as gr
+import os
+import torch
+
+from model import create_effnetb2_model
+from timeit import default_timer as timer
+from typings import Tuple, Dict
+import class_names
+
+# Setup class names
+with open(class_names.txt, 'r') as f:
+  class_names= [food_name.strip() for food_name in f.readlines()]
+
+
+# Model and transforms preparation
+effnetb2_model, effnetb2_transform= create_effnetb2_model()
+# Load state dict
+effnetb2_model.load_state_dict(torch.load(
+    f= 'effnetb2_food101_model.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 effnet b2
+  transform_image= effnetb2_transform(img).unsqueeze(0)
+
+  #put model into eval mode, make pred
+  effnetb2_model.eval()
+  with torch.inference_mode():
+    pred_logits= effnetb2_model(transform_image)
+    pred_prob= torch.softmax(pred_logits, dim=1)
+
+  # create a pred label and pred prob dict
+  pred_label_and_prob= {class_names[i]: float(pred_prob[0][i]) for i in range(len(class_names))}
+
+
+  # calc pred time
+  stop_time= timer()
+  pred_time= round(stop_time - start_time, 4)
+
+
+  # return pred dict and pred time
+  return pred_label_and_prob, pred_time
+
+# create example list
+example_list= [['example/'+example] for example in os.listdir('example')]
+
+# create gradio app
+title= 'FoodVision Large 🍕🥩🍣 '
+description= 'An EfficientnetB2 feature extractor Computer vision model to classify 101 classes of food from the food 101 image dataset'
+article= 'Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/).'
+
+# Create the gradio demo
+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
+                   )
+
+# Launch 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

effnetb2_food101_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc414d33be77a0e4a1e0c50bd6c69f683ea53bdaac5e4ae3abad09e28499ce7
+size 31833771

model.py

@@ -0,0 +1,24 @@
+
+import torch
+import torchvision
+from torch import nn
+
+def create_effnetb2_model(num_classes:int=101,
+                          seed:int=42):
+  # Create Effnet pretrained model
+  weights= torchvision.models.EfficientNet_B2_Weights.DEFAULT
+  transforms= weights.transforms()
+  model= torchvision.models.efficientnet_b2(weights=weights)
+
+  # Freeze all layers in the base model
+  for param in model.parameters():
+    param.requires_grad= False
+
+  # Change the classifier layer
+  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 +1,4 @@
+
+torch==2.0.1
+torchvision==0.15.2
+gradio==3.35.2