first commit

.gitattributes

@@ -29,3 +29,4 @@ 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
+09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth filter=lfs diff=lfs merge=lfs -text

09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0905213cdb284cea170521d1e7c5f65a37e85b08866740a0b8c4db0138b8ab8b
+size 31856609

app.py

@@ -0,0 +1,86 @@
+#!usr/bin/env python
+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
+from PIL import Image
+
+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=len(class_names)
+)
+
+effnetb2.load_state_dict(
+    torch.load(
+        f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
+def predict(img: Image) -> Tuple[Dict, float]:
+    """Transforms and performs a prediction on an image and returns the 
+    prediction and the time taken
+
+    Parameters
+    ----------
+    img : Image
+        an Image
+
+    Returns
+    -------
+    Tuple[Dict, float]
+        Tuple[prediction probabilities, time taken]
+    """
+
+    start = timer()
+    
+    # trasnform and add batch dimension
+    img = effnetb2_transforms(img).unsqueeze(0)
+
+    # put model on eval mode and turn on inference
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+    
+    # create a prediction label: prediction prob dict
+    pred_labels_and_probs = {
+        class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))
+    }
+
+    # calculate pred time
+    pred_time = round(timer() - start, 5)
+
+    return pred_labels_and_probs, pred_time
+
+### Gradio App
+
+title = "FoodVision Big"
+description = "An EfficientNetB2 frature extractor CV model to classify images of food"
+article = "TODO"
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+def main():
+# create Gradio interface
+    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()
+
+if __name__ == "__main__":
+    main()

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 +1,40 @@
+import torch
+import torchvision
+
+from torch import nn
+from typing import Tuple
+
+def create_effnetb2_model(
+    num_classes: int = 3, 
+    seed: int = 42) -> Tuple[torch.nn.Module, torchvision.transforms.Compose]:
+    """Creates an EfficientNetB2 feature extractor model and transforms
+
+    Parameters
+    ----------
+    num_classes : int, optional
+        Number of classes in the classifier head, by default 3
+    seed : int, optional
+        random seed value, by default 42
+
+    Returns
+    -------
+    Tuple[torch.nn.Module, torchvision.transforms.Compose]
+        Tuple[EffnetB2 feature extractor model, EffNetb2 image transforms]
+    """
+    # Create EffNetB2 pretrained weights, transforms and model
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights)
+
+    # freeze parameters
+    for param in model.parameters():
+        param.requires_grad = False
+    
+    # change classifier head
+    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 +1,5 @@
+torch
+torchvision
+torchmetrics
+requests
+tqdm