added the files to the repo

.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_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth filter=lfs diff=lfs merge=lfs -text

09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df742dbb48fecef3a11c84d17cc1c763812fa5d9e1bf117da2020f6268031a5
+size 31315203

app.py

@@ -0,0 +1,69 @@
+### 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
+class_names = ['pizza', 'steak', 'sushi']
+
+### 2. Model and transforms setup
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=3,
+)
+
+#Load the saved weights
+effnetb2.load_state_dict(torch.load(f="09_pretrained_effnetb2_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
+  transformed_image = effnetb2_transforms(img).unsqueeze(dim=0)
+
+  # Put model into eval mode, make prediction
+  effnetb2.eval()
+  with torch.inference_mode():
+    logits = effnetb2(transformed_image)
+    preds = torch.softmax(logits, dim=1)
+
+  # Create a prediction label and prediction probability dictionary
+  label = class_names[torch.argmax(preds)]
+  pred_labels_and_probs = {class_names[i]:float(preds[0][i]) for i in range(len(class_names))}
+
+  # Calaulate pred time
+  end_time = timer()
+  duration = round(end_time - start_time, 4)
+
+  # retrun pred dict and pred time
+  return pred_labels_and_probs, duration
+
+
+# Create title, description and article
+title = "Foodvision mini"
+description="An EfficientNetB2 feature extractor computer vision model to classify images as pizza, steak or sushi."
+article = "Created at 09. PyTorch model deployment ZTM course"
+
+# Create example list
+example_list = [["examples/" + examples] for examples in os.listdir("examples")]
+
+# Create the Gradio demo
+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)")],
+                    title=title,
+                    article=article,
+                    examples=example_list)
+
+# Launch the demo
+demo.launch(debug=False, # print errors locally?
+            share=True) # generate a publically shatrable URL

model.py

@@ -0,0 +1,38 @@
+import torch
+import torchvision
+
+from torch import nn
+from helper_functions import set_seeds
+
+def create_effnetb2_model(output_classes:int=3,
+                           seed=42):
+  """
+  Creates a pretrained EfficientNet B2 model feature extractor, with the base layers frozen and the output classifier adjusted to the target setup
+
+  returns:
+    (model, transforms)
+    model: The Feature extractor model instance of EfficientNetB2
+  """
+  # 1. Setup poretrained EffNetB2 weights
+  effnetb2_weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+
+  #2. Get the transforms
+  transforms = effnetb2_weights.transforms()
+
+  #3. Setup pretrines model instance
+  model = torchvision.models.efficientnet_b2(weights=effnetb2_weights)
+
+  #4. Freeze the base layers in the model - this will stop all base layers from training
+  for param in model.parameters():
+    param.requires_grad=False
+
+  #5. Change the classification head
+  #Set seed
+  set_seeds(42)
+  model.classifier = nn.Sequential(
+      nn.Dropout(p=0.3, inplace=True),
+      nn.Linear(in_features=1408,
+                out_features=output_classes,
+                bias=True)
+  )
+  return model, transforms

requirements.txt

@@ -0,0 +1,4 @@
+
+torch==2.10.0
+torchvision==0.25.0
+gradio==5.50.0