init

.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:eff07ee6a9faf1b1cbaf25837bd5990025f46ac083ea629919de57c82a86c157
+size 31314554

app.py

@@ -0,0 +1,66 @@
+
+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
+
+class_names = ["pizza", "steak", "sushi"]
+
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=len(class_names),
+)
+
+effnetb2.load_state_dict(
+    torch.load(
+        f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+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
+
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "Created using PyTorch"
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+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()

model.py

@@ -0,0 +1,21 @@
+
+import torch
+import torchvision
+from torch import nn
+
+def create_effnetb2_model(num_classes:int = 3, seed:int = 42):
+  weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+  transforms = weights.transforms()
+
+  model = torchvision.models.efficientnet_b2(weights=weights).to(device)
+
+  for param in model.parameters():
+    param.requires_grad = False
+
+  torch.manual_seed(seed)
+  model.classifier = nn.Sequential(
+    nn.Dropout(p=0.3, inplace=True),
+    nn.Linear(in_features=1408, out_features=num_classes, bias=True)
+  )
+
+  return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.5.1
+torchvision==0.20.1
+gradio==5.11.0