initial commit

app.py

@@ -0,0 +1,63 @@
+import os
+from timeit import default_timer as timer
+from typing import Tuple
+from pathlib import Path
+
+import gradio as gr
+import torch
+from torch import nn
+from torchvision import transforms
+
+from model import create_effnetb2_model
+
+class_names = ["pizza", "steak", "sushi"]
+device = "cpu"
+
+# Create model
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=len(class_names))
+
+# Load saved weights
+effnetb2.load_state_dict(torch.load("effnetb2.pth"), 
+                         map_location=torch.device(device))
+
+# Define predict function
+def predict(img: Image) -> Tuple[dict, float]:
+    """Uses EffnetB2 model to transform and predict on img. Returns prediction
+    probabilities and time taken.
+    
+    Args:
+      img (PIL.Image): Image to predict on.
+    
+    Returns:
+      A tuple (pred_labels_and_probs, pred_time), where pred_labels_and_probs
+      is a dict mapping each class name to the probability the model assigns to
+      it, and pred_time is the time taken to predict (in seconds).
+    """
+    start_time = timer()
+    img = effnetb2_transforms(img).unsqueeze(0)
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+    pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i])
+                             for i in range(len(class_names))}
+    pred_time = round(timer() - start_time, 4)
+    return pred_labels_and_probs, pred_time
+
+# Initialize Gradio app
+title = "FoodVision Mini"
+description = "EfficientNetB2 feature extractor to classify images of food as pizza, steak, or sushi."
+article = "From the [Zero to Mastery PyTorch tutorial](https://www.learnpytorch.io/09_pytorch_model_deployment/)"
+examples = [list(example) for example in Path("examples").glob("*.jpg")]
+
+demo = gr.Interface(
+    fn=predict,
+    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,
+)
+
+demo.lauch()

effnetb2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796022ec640571b749d822bb03ffaac90c49bded116726793cf9cc35e6b7109d
+size 31294149

model.py

@@ -0,0 +1,32 @@
+from typing import Tuple
+
+import torch
+from torch import nn
+import torchvision
+
+def create_effnetb2_model(num_classes: int = 3,
+                          seed: int = 4,
+                         ) -> Tuple[nn.Module, torchvision.Transforms]:
+    """Create an EfficientNetB2 feature extractor model and transforms.
+    
+    Args:
+      num_classes: Number of classes to use for classification (default 3).
+      seed: Random seed for reproducibility (default 4).
+      
+    Returns:
+      A tuple (model, transforms) of the model and its image transforms.
+    """
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = effnet_b2_weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights)
+    
+    # Freeze parameters below the head
+    for param in model.parameters():
+        param.requires_grad = False
+    # Replace the classifier head with one of appropriate size for the problem
+    torch.manual_seed(seed)
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=len(class_names))
+    )
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+gradio==3.37.0
+torch==2.0.1
+torchvision==0.15.2