add the final scripts

.gitattributes

@@ -33,3 +33,5 @@ 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
+.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:e3c46b8bce9fea760b9e2891199c70a41e577c40dba131904599c1ed9d43e757
+size 343273342

app.py

@@ -0,0 +1,66 @@
+### 1. Imports and class names setup ###
+from model import create_vitB16_model
+import torch
+from typing import Tuple, Dict
+from timeit import default_timer as timer
+import gradio as gr
+
+# Setup class names
+class_names = ['pizza', 'steak', 'sushi']
+
+### 2. Model and transforms perparation ###
+model, model_transforms = create_vitB16_model(num_classes=len(class_names))
+
+# Load save weights
+model.load_state_dict(torch.load(f='09_pretrained_vit_feature_extractor_pizza_steak_sushi_20_percent.pth',
+                                 map_location='cpu'))
+
+# 3. Predict Function
+
+def predict(img) -> Tuple[Dict, float]:
+  # Start a timer
+  start_time = timer()
+
+  # Transform the input image for use with vitB16
+  img = model_transforms(img).unsqueeze(dim=0)
+
+  # Put model into eval mode, make prediction
+  model.eval()
+  with torch.inference_mode():
+    # Pass transformed image through the model and turn the prediction logits into probabilities
+    pred_logit = model(img)
+    pred_prob = torch.softmax(pred_logit, dim=1)
+
+  # Create a prediction label and prediction probability dictionary
+  pred_labels_and_probs = {class_names[i]: float(pred_prob[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 [vision Transformer B16 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.vit_b_16.html) computer vision model to classify images as pizza, steak or sushi."
+article = "Created with 🤎 (and a mixture of mathematics, statistics, and tons of calculations 👩🏽‍🔬)"
+
+# Create example list
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+demo = gr.Interface(fn=predict,
+                    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 publically shareable URL 

model.py

@@ -0,0 +1,25 @@
+import torch, torchvision
+def create_vitB16_model(num_classes: int=3, seeds: int = 42):
+
+  # 1. Setup pretrained viT Weights
+  weights = torchvision.models.ViT_B_16_Weights.DEFAULT
+
+  # 2. Get transforms
+  transforms = weights.transforms()
+
+  # 3. Setup pretrained instance
+  model = torchvision.models.vit_b_16(weights=weights)
+
+  # 4. Freeze the base layers in the model (this will stop all layers from training)
+  for params in model.parameters():
+    params.requires_grad = False
+
+  # Set seeds for reproducibility
+  torch.manual_seed(seeds)
+
+  # 5. Modify the number of output layers
+  model.heads = torch.nn.Sequential(
+      torch.nn.Linear(in_features=768, out_features=num_classes, bias=True)
+  )
+
+  return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.4.0
+torchvision==0.19.0
+gradio==4.44.0