Upload 5 files

app.py

@@ -0,0 +1,86 @@
+### 1. Imports and class names setup ### 
+import gradio as gr
+import os
+import torch
+
+from model import create_efficientnet_b0_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# Setup class names
+class_names = ['CRVO',
+  'Choroidal Nevus',
+  'Diabetic Retinopathy',
+  'Laser Spots',
+  'Macular Degeneration',
+  'Macular Hole',
+  'Myelinated Nerve Fiber',
+  'Normal',
+  'Pathological Mypoia',
+  'Retinitis Pigmentosa']
+
+### 2. Model and transforms preparation ###
+
+# Create EfficientNet_B0 model
+efficientnet_b0, efficientnet_b0_transforms = create_efficientnet_b0_model(
+    num_classes=len(class_names), # actual value would also work
+)
+
+# Load saved weights
+efficientnet_b0.load_state_dict(
+    torch.load(
+        f="pretrained_efficientnet_b0_feature_extractor_drappcompressed.pth",
+        map_location=torch.device("cpu"),  # load to CPU
+    )
+)
+
+### 3. Predict function ###
+
+# Create predict function
+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 = efficientnet_b0_transforms(img).unsqueeze(0)
+    
+    # Put model into evaluation mode and turn on inference mode
+    efficientnet_b0.eval()
+    with torch.inference_mode():
+        # Pass the transformed image through the model and turn the prediction logits into prediction probabilities
+        pred_probs = torch.softmax(efficientnet_b0(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 = "DeepFundus 👀"
+#description = "A EfficientNet_B0 feature extractor computer vision model to classify funduscopic images."
+#article = "Created with the help from [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.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 +1,36 @@
+import torch
+import torchvision
+
+from torch import nn
+
+def create_efficientnet_b0_model(num_classes:int=10, # 4
+                          seed:int=42):
+    """Creates an EfficientNet_B0 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): EfficientNet_B0 feature extractor model. 
+        transforms (torchvision.transforms): EfficientNet_B0 image transforms.
+    """
+    # 1, 2, 3. Create EfficientNet_B0 pretrained weights, transforms and model
+    weights = torchvision.models.EfficientNet_B0_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b0(weights=weights)
+
+    # 4. Freeze all layers in base model
+    for param in model.parameters():
+        param.requires_grad = True # Set to False for model's other than ResNet
+
+    # 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=1280
+                  , out_features=num_classes), # If using EffnetB2 in_features = 1408, EffnetB0 in_features = 1280, if ResNet50 in_features = 2048
+    )
+    
+    return model, transforms