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
+pretrained_effnetb2_feature_extractor_oxfordPets.pth filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,81 @@
+### 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
+with open("class_names.txt", "r") as f: # reading them in from class_names.txt
+    class_names = [pet_name.strip() for pet_name in  f.readlines()]
+    
+### 2. Model and transforms preparation ###    
+
+# Create model
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=len(class_names)
+)
+
+# Load saved weights
+effnetb2.load_state_dict(
+    torch.load(
+        f="pretrained_effnetb2_feature_extractor_oxfordPets.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 = effnetb2_transforms(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 = "PetVision 🐱👁"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of pets into [37 different classes](https://raw.githubusercontent.com/Alejandro-Casanova/pytorch-deep-learning/main/extras/oxfordPets_class_names.txt)."
+article = "Created by Alejandro Casanova, following the course by [Daniel Bourke](https://www.learnpytorch.io/)"
+
+# Create examples list from "examples/" directory
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create Gradio interface 
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=[
+        gr.Label(num_top_classes=5, label="Predictions"),
+        gr.Number(label="Prediction time (s)"),
+    ],
+    examples=example_list,
+    title=title,
+    description=description,
+    article=article,
+)
+
+# Launch the app!
+demo.launch()

class_names.txt

@@ -0,0 +1,37 @@
+Abyssinian
+American Bulldog
+American Pit Bull Terrier
+Basset Hound
+Beagle
+Bengal
+Birman
+Bombay
+Boxer
+British Shorthair
+Chihuahua
+Egyptian Mau
+English Cocker Spaniel
+English Setter
+German Shorthaired
+Great Pyrenees
+Havanese
+Japanese Chin
+Keeshond
+Leonberger
+Maine Coon
+Miniature Pinscher
+Newfoundland
+Persian
+Pomeranian
+Pug
+Ragdoll
+Russian Blue
+Saint Bernard
+Samoyed
+Scottish Terrier
+Shiba Inu
+Siamese
+Sphynx
+Staffordshire Bull Terrier
+Wheaten Terrier
+Yorkshire Terrier

flagged/Predictions/tmppt66_mjs.json

@@ -0,0 +1 @@
+{}

flagged/log.csv

@@ -0,0 +1,2 @@
+img,Predictions,Prediction time (s),flag,username,timestamp
+,C:\Users\alex\Desktop\PetVision\flagged\Predictions\tmppt66_mjs.json,,,,2023-10-04 22:44:46.311654

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

pretrained_effnetb2_feature_extractor_oxfordPets.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac943853bf13dae674ea0b9844fb19c3d0d77e3e6e8da6ee5042183e680abdcf
+size 31489783

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.0.1
+torchvision==0.15.2
+gradio==3.46.1