Foodvision mini files made on Jupyter Notebook

10_pretrained_effnetb2_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c766015cd794095e568aa5b7b92da0f29c28fd693b2fd0d9af2f360cede424
+size 31287125

app.py

@@ -0,0 +1,74 @@
+
+### 1. Import and class names setup   ###
+import torch
+import torchvision
+import gradio as gr
+import os
+
+from torch import nn
+from model import create_effnetb2_model
+from typing import Tuple, Dict
+from timeit import default_timer as timer
+
+# Setup class names
+class_names = ['pizza', 'steak', 'sushi']
+
+
+### 2. Model and transforms preparation  ###
+effnetb2, effnetb2_transforms = create_effnetb2_model()
+
+# Load save weights
+effnetb2.load_state_dict(
+    torch.load(
+        f="10_pretrained_effnetb2_20_percent.pth",
+        map_location=torch.device('cpu')           # ensure it loads in cpu
+    )
+)
+
+
+### 3. Predict function  ###
+def predict(img) -> Tuple[Dict, float]:
+    # Start a timer
+    start_time = timer()
+        
+    # Transform the input image for use with EffNetB2
+    transformed_image = effnetb2_transforms(img).unsqueeze(0)  # Adding batch_dim
+
+    # Put model into eval mode, make prediction
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_prob = torch.softmax(effnetb2(transformed_image), dim=1)
+    
+    # Create a prediction label and prediction probability dict
+    pred_labels_and_probs = {class_names[i]: float(pred_prob[0][i]) for i in range(len(class_names))}
+    
+    # Calculate pred time
+    end_time = timer()
+    pred_time = round(end_time - start_time, 4)
+    
+    return pred_labels_and_probs, pred_time
+
+
+
+### 4. Gradio App
+
+# Create title, description and article
+title = "FoodVision Mini 🥩🍕🍥"
+description = "An EfficientNetB2 feature extractor CV model to classify food"
+article = "Created at 10. PyTorch Model Deployment"
+
+# Create example list
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+# Create the Gradio Demo
+demo = gr.Interface(fn=predict,  #maps input to output
+                   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.launch(debug=False,  #print errors locally?
+           share=True)

model.py

@@ -0,0 +1,26 @@
+
+import torch
+import torchvision
+
+from torch import nn
+
+def create_effnetb2_model(num_classes: int=3,
+                         seed: int=42):
+    # 1, 2, 3 Create Effnetb2 weights, transform 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 the classifier head with seed42
+    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==2.0.0
+torchvision==0.15.0
+gradio==3.23.0