Upload 7 files

.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
+examples/04-pizza-dad.jpeg 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:b08ce4e44b96da99da749e72162a9ec231dcae84a544f2cf01216ed2b7a66a4f
+size 31856609

README.md

@@ -1,12 +1,13 @@
 ---
 title: FoodVision Big
-emoji: 📈
-colorFrom: indigo
-colorTo: green
+emoji: 🚀
+colorFrom: green
+colorTo: blue
 sdk: gradio
-sdk_version: 4.2.0
+sdk_version: 3.42.0
 app_file: app.py
 pinned: false
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+import os
+import torch
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+from model import create_effnetb2_model
+
+with open("class_names.txt", "r") as f:
+    class_names = [food.strip() for food in f.readlines()]
+
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=101)
+
+effnetb2.load_state_dict(
+    torch.load(
+        f="09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth",
+        map_location=torch.device("cpu"),
+    )
+)
+
+
+def predict(img) -> Tuple[Dict, float]:
+    start = timer()
+
+    img = effnetb2_transforms(img).unsqueeze(0)
+
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+
+    pred_labels_and_probs = {
+        class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))
+    }
+
+    end = timer()
+    pred_time = round(end - start, 4)
+
+    return pred_labels_and_probs, pred_time
+
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+
+app = 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="FoodVision Big",
+    description="An EFficientNetB2 feature extractor for 101 food classes",
+    article="Created at [09_model_deployment]",
+)
+
+app.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 +1,41 @@
+import torch
+from torch import nn
+import torchvision
+import os
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+
+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
+
+
+def pred(img, effnetb2, effnetb2_transforms, class_names) -> Tuple[Dict, float]:
+    start = timer()
+
+    img = effnetb2_transforms(img).unsqueeze(0)
+
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+
+    pred_labels_and_probs = {
+        class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))
+    }
+
+    end = timer()
+    pred_time = round(end - start, 4)
+
+    return pred_labels_and_probs, pred_time

requirements.txt

@@ -0,0 +1,3 @@
+torch
+torchvision
+gradio