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/25525.jpg filter=lfs diff=lfs merge=lfs -text

BiteVision101_e20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3e4f6618d6bc1d1794f312b840d31e855bc4d604a61292dfb2a423ac4d5f4f
+size 31824378

app.py

@@ -0,0 +1,50 @@
+import gradio as gr
+import bitevision_model 
+import torch
+from timeit import default_timer as timer
+import os
+
+effnetb2, effnetb2_transforms=bitevision_model.create_effnetb2(101,42)
+
+effnetb2.load_state_dict(torch.load("BiteVision101_e20.pth", only_weights=True, map_location=torch.device("cpu"), weights_only=True))
+
+classes=['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']
+
+def make_pred_and_timeit(img):
+
+    start_timer=timer()
+    
+    transformed_image=effnetb2_transforms(img).unsqueeze(dim=0)
+    pred_logits=effnetb2(transformed_image)
+    
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_logits=effnetb2(transformed_image)
+        probs=torch.softmax(pred_logits, dim=1).squeeze()
+        
+    pred_probs={classes[i]: round(probs[i].detach().numpy().item(),3) for i in range(len(probs))}
+    pred_time=timer()-start_timer
+    
+    return pred_probs, pred_time
+
+examples=[['examples'+example] for example in os.listdir("examples")]
+
+title="BiteVision101: FoodImage Classification Model 🍔 🍕 🥑"
+description="🍔 BiteVision101 🍕 is the ultimate food detective! 🕵️‍♂️🍽️ Simply upload an image of any food, and it will instantly identify the dish and tell us its name! 🥑✨ From a mouthwatering pizza 🍕 to a juicy burger 🍔 or a vibrant salad 🥗, BiteVision101 has got it covered! 🎉📸 No need to guess, just snap a pic and let the magic happen! ✨🙌"
+article="BiteVision101 is a feature extraction model trained on the Food-101 dataset, leveraging EfficientNetB2 as its backbone. With a total of 7843303 parameters, BiteVision101 delivers powerful performance in food image recognition."
+demo=gr.Interface(fn=make_pred_and_timeit, inputs=gr.Image(type="pil"), outputs=[gr.Label(num_top_classes=3, label="Predictions"), 
+                                                                     gr.Number(label="Prediction Time(s)")], examples=examples, 
+                  title=title, description=description, article=article)
+
+demo.launch()
+
+

bitevision_model.py

@@ -0,0 +1,22 @@
+import torch
+import torchvision
+
+def create_effnetb2(num_classes:int=101, seed:int=42, device:str="cpu"):
+    
+    weights=torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    effnetb2=torchvision.models.efficientnet_b2(weights=weights).to(device)
+    
+    for params in effnetb2.parameters():
+        params.requires_grad=False
+        
+    torch.manual_seed(seed)
+    effnetb2.classifier=torch.nn.Sequential(
+        torch.nn.Dropout(p=0.3, inplace=True),
+        torch.nn.Linear(in_features=1408, out_features=101)
+        )
+    
+    effnetb2_transforms=weights.transforms()
+    
+    return effnetb2, effnetb2_transforms
+
+

requirements.txt

@@ -0,0 +1,3 @@
+torch=2.5.1
+torchvision=0.20.1
+gradio=5.20.1