First commit

07_effnetb2_data_50_percent_10_epochs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc265ff27b5ff26522a292f8039b4c910a49f4a8754ef4b90aafc7d1f00f9f6
+size 31273033

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:e65879e63a119f1dcc76e8928790aac49373e4bc1d29c0208b7e7c6f88dee2bb
+size 31273033

app.py

@@ -0,0 +1,91 @@
+
+### 1. Imports and class names setup ###
+import gradio as gr
+import os
+import torch
+import torchvision.transforms as T
+
+from model import create_effnet_b2
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+class_names = ['pizza', 'steak', 'sushi']
+
+### 2. Model and transforms preparation ###
+test_tsfm = T.Compose([T.Resize((224,224)),
+                        T.ToTensor(),
+                       T.Normalize(mean=[0.485, 0.456, 0.406], # 3. A mean of [0.485, 0.456, 0.406] (across each colour channel)
+                         std=[0.229, 0.224, 0.225]) # 4. A standard deviation of [0.229, 0.224, 0.225] (across each colour channel),
+                       ])
+
+# Create EffNetB2 Model
+effnetb2, test_transform = create_effnet_b2(num_of_class=len(class_names), 
+                            transform=test_tsfm,
+                            seed=42)
+
+# saved_path = 'demos\foodvision_mini\09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth'
+saved_path = '07_effnetb2_data_50_percent_10_epochs.pth'
+
+print('Loading Model State Dictionary')
+# Load saved weights
+effnetb2.load_state_dict(
+                torch.load(f=saved_path,
+                           map_location=torch.device('cpu'), # load to CPU
+                          )
+                        )
+
+print('Model Loaded ...')
+### 3. Predict function ###
+
+# Create predict function
+from typing import Tuple, Dict
+
+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 = test_tsfm(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
+
+### 4. Gradio App ###
+
+# Create title, description and article strings
+title= 'FoodVision Mini 🍕🥩🍣'
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)."
+
+
+# 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.inputs.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
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article
+                   )
+# Launch the demo
+print('Gradio Demo Launched')
+demo.launch()

model.py

@@ -0,0 +1,44 @@
+
+import torch
+import torch.nn as nn
+import torchvision
+
+
+# Create an EffNetB2 feature extractor
+def create_effnet_b2(num_of_class: str=3,
+                     transform: torchvision.transforms=None,
+                     seed=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. Get the base mdoel with pretrained weights and send to target device
+    model = torchvision.models.efficientnet_b2(pretrained=True)
+    
+    # 2. Freeze the base model layers
+    for param in model.parameters():
+        param.requires_grad = False
+    
+    # 3. Set the seeds    
+    torch.manual_seed(seed)
+    
+    # 4. Change the classifier head
+    model.classifier = nn.Sequential(nn.Dropout(p=0.3, inplace=True),
+                                     nn.Linear(1408, num_of_class, bias=True)
+                                    )
+    
+    return model, transform
+
+# mymodel = create_effnet_b2(num_of_class=3, 
+#                            transform=torchvision.transforms.Compose([torchvision.transforms.ToTensor()]),
+#                            seed=42)
+# print(mymodel)

requirements.txt

@@ -0,0 +1,4 @@
+
+torch==1.10.0
+torchvision==0.11.0+cu102
+gradio==3.16.2