adding all files 062023 -kaiku

app.py

@@ -0,0 +1,178 @@
+### 1. Imports and class names setup ###
+import gradio as gr
+import os
+import torch
+
+from model import create_vit_b_16_swag
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+class_names = ['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']
+
+### 2. Model and transforms preparation ###
+
+# Create EffNetB0 model
+vit_b_16_swag, vit_b_16_swag_transforms = create_vit_b_16_swag()
+
+# Load saved weights
+vit_b_16_swag.load_state_dict(
+    torch.load(
+        f="vit_b_16_swag_20percent_10epoch.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+
+### 3. Predict function ###
+
+# Create predict function
+def predict(img) -> Tuple[Dict, float]:
+    """Transforms and performs a prediction on img and returns prediction and time taken.
+    """
+    # Start the timer
+    start_time = timer()
+
+    # Transform the target image and add a batch dimension
+    img = vit_b_16_swag_transforms(img).unsqueeze(0)
+
+    # Put model into evaluation mode and turn on inference mode
+    vit_b_16_swag.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(vit_b_16_swag(img), dim=1)
+
+    # Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+    # Calculate the prediction time
+    pred_time = round(timer() - start_time, 5)
+
+    # Return the prediction dictionary and prediction time
+    return pred_labels_and_probs, pred_time
+
+
+### 4. Gradio app ###
+
+# Create title, description and article strings
+title = "Food Classifier V1"
+description = " 20 Percent Food 101 on Vit_b_16 SWAG"
+article = "Created at google collab. Documentation at https://medium.com/me/stories/public, Code repository at https://github.com/Alyxx-The-Sniper/CNN "
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo = gr.Interface(fn=predict,  # mapping function from input to output
+                    inputs=gr.Image(type="pil"),  # what are the inputs?
+                    outputs=[gr.Label(num_top_classes=4, label="Predictions"),  # what are the outputs?
+                             gr.Number(label="Prediction time (s)")],
+                    # our fn has two outputs, therefore we have two outputs
+                    # Create examples list from "examples/" directory
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article)
+
+# Launch the demo!
+demo.launch()

model.py

@@ -0,0 +1,22 @@
+import torchvision
+from torch import nn
+
+def create_vit_b_16_swag(num_classes:int=101, seed:int=42):
+    # 1. Get the base mdoel with pretrained weights and send to target device
+    weights = torchvision.models.ViT_B_16_Weights.IMAGENET1K_SWAG_E2E_V1
+    transforms = weights.transforms()
+    model = torchvision.models.vit_b_16(weights=weights)#.to(device)
+
+    # 2. Freeze the base model layers
+    for param in model.parameters():
+        param.requires_grad = False
+
+
+    # 3. Change the heads
+    model.heads = nn.Linear(in_features=768,
+                            out_features=101)#.to(device)
+
+    # 5. Give the model a name
+    model.name = "vit_b_16_swag"
+    print(f"[INFO] Created new {model.name} model.")
+    return model, transforms

requirements.txt

@@ -0,0 +1,6 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4
+
+output:
+Writing demos/food_classification/requirements.txt

vit_b_16_swag_20percent_10epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2c4355cf30acf7454a3ee728c981de2e1913b9b1a7bfa2373f8bcbe40c0ecb
+size 344736321