first commit

.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:cb9e3a8c694c7a5302fdae148c2f7b46ce7fd77a09a8aa727fe0fdc50a802d3c
+size 31313869

app.py

@@ -0,0 +1,77 @@
+### 1. Imports and class names setup (步驟1) ###
+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 (步驟2) ###
+"""Create EffNetB2 model: 獲得模型定義與變換"""
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=3) # (len(class_names) would also work)
+
+# Load save weights
+"""加載權重到模型"""
+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 (步驟3) ### 
+"""Create predict function: 建立預測函數 (from 7.2)"""
+def predict(img) -> Tuple[Dict, float]:
+  # Start a timer
+  start_time = timer()
+
+  # Transform the input image for use with EffNetB2
+  """Transform the target image and add a batch dimension"""
+  img = effnetb2_transforms(img).unsqueeze(0) # unsqueeze = add batch dimension on 0th index
+
+  # Put model into eval mode, make prediction (Put model into evaluation mode and turn on inference mode)
+  effnetb2.eval()
+  with torch.inference_mode():
+    # Pass transformed image through the model and turn the prediction logits into probaiblities
+    """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 pred time (prediction time)
+  end_time = timer()
+  pred_time = round(end_time - start_time, 4)
+
+  # Return pred dict and pred time (the prediction dictionary and prediction time)
+  return pred_labels_and_probs, pred_time
+
+### 4. Gradio app (步驟4) ### 
+"""(from 7.4)"""
+# Create title, description and article (strings)
+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 (from "examples/" directory)
+"""(based on 8.3)"""
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio demo
+demo = gr.Interface(fn=predict, # maps inputs to outputs #( 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 +1,35 @@
+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):
+  """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.
+  """
+  # 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==3.45.0