initial commit

.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
+09_pretrained_vit_feature_extractor_pizza_steak_sushi_20_percent.pth filter=lfs diff=lfs merge=lfs -text

09_pretrained_vit_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3363d8b4126848fe1cc4b6ac1eef130ec2de18da1221b330428e1d44901ec6b0
+size 343271805

app.py

@@ -0,0 +1,71 @@
+### 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 ###
+vit, vit_transforms = create_vit_model(num_classes = 3)
+
+# Load saved weights
+vit.load_state_dict(
+    torch.load(
+        f = "09_pretrained_vit_feature_extractor_pizza_steak_sushi_20_percent.pth",
+        map_location = torch.device("cpu") # load the model to the CPU
+    )
+)
+
+### 3. Predict function ###
+
+def predict(img) -> Tuple[Dict, float]:
+    # Start a timer
+    start_time = timer()
+
+    # Transform the input image for use with ViT
+    img = vit_transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index
+
+    # Put model into eval mode, make prediction
+    vit.eval()
+    with torch.inference_mode():
+        # Pass transformed image through the model and turn the prediction logits into probabilities
+        pred_probs = torch.softmax(vit(img), dim = 1)
+
+    # Create a prediction label and prediction probability dictionary
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+    # Calculate pred time
+    end_time = timer()
+    pred_time = round(end_time - start_time, 4)
+
+    # Return pred dict and pred time
+    return pred_labels_and_probs, pred_time
+
+### 4. Gradio app ###
+
+# Create title, description, and article
+title = "FoodVision Mini 🍕🥩🍣"
+description = "A [ViT transformer feature extractor](https://docs.pytorch.org/vision/main/models/generated/torchvision.models.vit_b_16.html#vit-b-16) computer vision model to classify images as pizza, steak, or sushi."
+article = "Created at [turtlemb's GitHub](https://github.com/turtlemb)."
+
+# Create example list
+example_list = [["examples/" + example] for example in os.listdir(examples)]
+
+# Create the Gradio demo
+demo = gr.Interface(fn = predict, # maps inputs to outputs
+                    inputs = gr.Image(type = "pil"),
+                    outputs = [gr.Label(num_top_classes = 3, label = "Predictions"),
+                               gr.Number(label = "Prediction time (s)")],
+                    examples = example_list,
+                    title = title,
+                    description = description,
+                    article = article)
+
+# Launch the demo
+demo.launch(debug = False, # print errors locally?
+            share = True) # generate a publicly shareable URL

model.py

@@ -0,0 +1,23 @@
+
+import torch
+import torchvision
+
+from torch import nn
+
+def create_vit_model(num_classes: int = 3,
+                     seed: int = 42):
+    # Create ViT_B_16 pre-trained weights, transforms and model
+    weights = torchvision.models.ViT_B_16_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.vit_b_16(weights = weights)
+
+    # Freeze all of the base layers
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head to suit our needs
+    torch.manual_seed(seed)
+    model.heads = nn.Sequential(nn.Linear(in_features = 768,
+                                          out_features = num_classes))
+
+    return model, transforms

requirements.txt

@@ -0,0 +1,4 @@
+
+torch==2.7.1
+torchvision==0.22.1
+gradio==6.9.0