First Commit

09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a562ae6c3fb899b49658e4e0a2e6cf8145e65265ea9252e99228cf4cea9afd4
+size 31307450

README.md

@@ -1,10 +1,10 @@
 ---
 title: FoodVision Mini
 emoji: 🚀
-colorFrom: green
-colorTo: red
+colorFrom: red
+colorTo: gray
 sdk: gradio
-sdk_version: 5.25.2
+sdk_version: 5.24.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -0,0 +1,67 @@
+
+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 
+
+class_names = ['pizza', 'steak', 'sushi']
+
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes = 3)
+
+effnetb2.load_state_dict(
+   torch.load(
+       f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.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
+
+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.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(share=False)

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+09_pretrained_effnetb2_feature_extractor_food101_20_percent.pth filter=lfs diff=lfs merge=lfs -text

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

requirements.txt

@@ -0,0 +1,5 @@
+torch == 1.12.0
+torchvision == 0.13.0
+gradio==3.50.2
+httpx==0.24.1
+httpcore==0.17.3