Upload 9 files

app.py

@@ -1,80 +1,80 @@
-### 1. Imports 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 typing import Tuple, Dict
-
-# Setup class names
-with open("class_names.txt", "r") as f: # reading them in from class_names.txt
-    class_names = [food_name.strip() for food_name in  f.readlines()]
-
-### 2. Model and transforms preparation ###
-
-# Create model
-effnetb2, effnetb2_transforms = create_effnetb2_model(
-    num_classes=101, # could also use len(class_names)
-)
-
-# Load saved weights
-effnetb2.load_state_dict(
-    torch.load(
-        f="pretrained_effnetb2_feature_extractor_food101.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 = effnetb2_transforms(img).unsqueeze(0)
-
-    # Put model into evaluation mode and turn on inference mode
-    effnetb2.eval()
-    with torch.inference_mode():
-        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
-        pred_probs = torch.softmax(effnetb2(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 = "FoodVision Big 🍔👁"
-description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into [101 different classes](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt)."
-
-# Create examples list from "examples/" directory
-example_list = [["examples/" + example] for example in os.listdir("examples")]
-
-# 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,
-)
-
-# Launch the app!
-demo.launch()
+### 1. Imports 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 typing import Tuple, Dict
+
+# Setup class names
+with open("class_names.txt", "r") as f: # reading them in from class_names.txt
+    class_names = [food_name.strip() for food_name in  f.readlines()]
+
+### 2. Model and transforms preparation ###
+
+# Create model
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=101, # could also use len(class_names)
+)
+
+# Load saved weights
+effnetb2.load_state_dict(
+    torch.load(
+        f="pretrained_effnetb2_feature_extractor_food101.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 = effnetb2_transforms(img).unsqueeze(0)
+
+    # Put model into evaluation mode and turn on inference mode
+    effnetb2.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(effnetb2(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 = "FoodVision Big 🍔👁"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food into [101 different classes](https://github.com/mrdbourke/pytorch-deep-learning/blob/main/extras/food101_class_names.txt)."
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# 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,
+)
+
+# Launch the app!
+demo.launch()

model.py

@@ -1,35 +1,36 @@
-import torch
-import torchvision
-
-from torch import nn
-
-
-def create_effnetb2_model(num_classes:int=3,
-                          seed:int=42):
-    """Creates an EfficientNetB2 feature extractor model and transforms.
-
-    Args:
-        num_classes (int, optional): number of classes in the classifier head.
-            Defaults to 3.
-        seed (int, optional): random seed value. Defaults to 42.
-
-    Returns:
-        model (torch.nn.Module): EffNetB2 feature extractor model.
-        transforms (torchvision.transforms): 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 all layers in base model
-    for param in model.parameters():
-        param.requires_grad = False
-
-    # Change classifier head with random seed for reproducibility
-    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
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_effnetb2_model(num_classes:int=3,
+                          seed:int=42):
+    """Creates an EfficientNetB2 feature extractor model and transforms.
+
+    Args:
+        num_classes (int, optional): number of classes in the classifier head.
+            Defaults to 3.
+        seed (int, optional): random seed value. Defaults to 42.
+
+    Returns:
+        model (torch.nn.Module): EffNetB2 feature extractor model.
+        transforms (torchvision.transforms): 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 all layers in base model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head with random seed for reproducibility
+    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

pretrained_effnetb2_feature_extractor_food101.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e05de434aa004ffcb2d82bd1fca54a2628e8fdcda893c6ec4e0332e54fd91b49
+size 31849018