first commit

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:a78dc0038266acfbb92e016f69eab2669b27013d998be16cbb7d46d063c7c60c
+size 31307450

app.py

@@ -0,0 +1,46 @@
+
+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=3)
+
+effnetb2.load_state_dict(torch.load(f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent",
+                                    map_location=torch.device("cpu")))
+
+def predict(img) -> Tuple[Dict, float]:
+  start_time = timer()
+
+  img = effnetb2_transforms(img).unsqueeze(0)
+
+  effnetb2.eval()
+  with torch.inference_mode():
+    pred_probs = torch.softmax(effnetb2(img), dim=1)
+  
+  pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
+
+  pred_time = round(timer() - start_time, 5)
+
+  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 by Nitin M."
+
+  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=examples_list,
+                      title=title,
+                      description=description,
+                      article=article)
+  
+  demo.launch()

model.py

@@ -0,0 +1,36 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_effnetb2_model(num_classes:int=3, 
+                          seed:int=42):
+    """Creates an EfficientNetB2 feature extractor model and transforms.
+
+    Args:
+        num_classes (int, optional): number of classes in the classifier head. 
+            Defaults to 3.
+        seed (int, optional): random seed value. Defaults to 42.
+
+    Returns:
+        model (torch.nn.Module): EffNetB2 feature extractor model. 
+        transforms (torchvision.transforms): EffNetB2 image transforms.
+    """
+    # Create EffNetB2 pretrained weights, transforms and model
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights)
+
+    # Freeze all layers in base model
+    for param in model.parameters():
+        param.requires_grad = False
+
+    # Change classifier head with random seed for reproducibility
+    torch.manual_seed(seed)
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes),
+    )
+    
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.1.0
+torchvision==0.16.0
+gradio==4.10.0