ViT model v1

app.py

@@ -0,0 +1,85 @@
+### 1. Imports and class names setup ###
+import gradio as gr
+import os
+import torch
+
+from model import create_vit_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+class_names = ["pizza", "steak", "sushi"]
+
+### 2. Model and transforms preparation ###
+
+# Create EffNetB2 model
+vit, vit_transforms = create_vit_model(
+    num_classes=3,  # len(class_names) would also work
+)
+
+# Load saved weights
+vit.load_state_dict(
+    torch.load(
+        f="classify_vit_b_16_20_percent_pizza_sushi_steak.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_transforms(img).unsqueeze(0)
+
+    # Put model into evaluation mode and turn on inference mode
+    vit.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(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 Classification"
+description = "A vision transformer feature extractor model to classify images of food as pizza, steak or sushi."
+article = "Reference: [Zero to Mastery Learn PyTorch for Deep Learning](https://www.learnpytorch.io/)."
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+print(torch.__version__)
+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=3, 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()

classify_vit_b_16_20_percent_pizza_sushi_steak.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a04ec26eb9ba8173e7d818d5979a9c2bdbecb3143be9e6ca51482d1509a929d1
+size 343269895

model.py

@@ -0,0 +1,22 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_vit_model(num_classes: int = 3, seed: int = 42):
+    weights = torchvision.models.ViT_B_16_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.vit_b_16(weights=weights)
+
+    # 4. Freeze all layers in base model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # 5. Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
+    model.heads = nn.Sequential(
+        nn.Linear(in_features=768, out_features=num_classes),
+    )
+
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==1.12.0
+torchvision==0.13.0
+gradio==3.1.4