Upload 7 files

09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aac3eef95daad4216793edc931ae737d24f47dd8cf6a9c496b9a93fcee62f2a
+size 31307450

app.py

@@ -0,0 +1,73 @@
+### 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 perparation ###
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=3)
+
+# Load save 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 for use with EffNetB2
+  img = effnetb2_transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index
+
+  # Put model into eval mode, make prediction
+  effnetb2.eval()
+  with torch.inference_mode():
+    # Pass transformed image through the model and turn the prediction logits into probaiblities
+    pred_probs = torch.softmax(effnetb2(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 = "An [EfficientNetB2 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) computer vision model to classify images as pizza, steak or sushi."
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/#74-building-a-gradio-interface)."
+
+# 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()

model.py

@@ -0,0 +1,24 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_effnetb2_model(num_classes:int=3, # default output classes = 3 (pizza, steak, sushi)
+                          seed:int=42):
+  # 1, 2, 3 Create EffNetB2 pretrained weights, transforms and model
+  weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+  transforms = weights.transforms()
+  model = torchvision.models.efficientnet_b2(weights=weights)
+
+  # 4. Freeze all layers in the base model
+  for param in model.parameters():
+    param.requires_grad = False
+
+  # 5. 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==1.12.0
+torchvision==0.13.0
+gradio==3.1.4