FoodVision Mini Initial commit

.gitattributes

@@ -33,3 +33,5 @@ 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
+09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth filter=lfs diff=lfs merge=lfs -text
+.pth filter=lfs diff=lfs merge=lfs -text

09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295250b9a37aff1ebe63f1e1b177a242468e2687614ad20c49c065af0d1bb5fb
+size 31314554

app.py

@@ -0,0 +1,80 @@
+
+### 1. Import 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
+class_names = ['pizza', 'steak', 'sushi']
+
+
+### 2. Model and Transforms perparation ###
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=3)
+
+# Load save weights
+effnetb2.load_state_dict(
+    torch.load(
+        f="09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pth",
+        map_location=torch.device("cpu")
+    )
+)
+
+### 3. Predict fucntin ###
+ 
+def predict(img) -> Tuple[Dict, float]:
+  # Start a timer
+  start_time = timer()
+  # Transform the input image for use with EffNetB2
+  transform_img = effnetb2_transformer(img).unsqueeze(0)
+
+  # Put model into eval mode, main prediction
+  effnetb2.eval()
+  with torch.inference_mode():
+    pred=effnetb2(transform_img)
+    pred_prob = torch.softmax(pred,dim=1)
+
+
+
+    
+
+  end_time = timer()
+  # Create a prediction label and prediction probability dictionary
+  pred_labels_and_probs = {class_names[i]:float(pred_prob[0][i]) for i in range(len(class_names))}
+  
+  # Calculate pred time
+  time = round(end_time-start_time,4)
+
+  # Return pred dict and pred time
+  return pred_labels_and_probs,time
+
+
+### 4. Gradio app ###
+
+# Create title , description and article
+title = "FoodVision Mini 🍕🥩🍣"
+description = " An [EfficinetNetB2](https://pytorch.org/vision/main/models/generated/torchvision.models.efficientnet_b2.html) feature extractor computer vision model to classify images as pizza, steak, sushi"
+article = "Created at [09. PyTorch Model Deployment](https://www.learnpytorch.io/09_pytorch_model_deployment/)"
+
+# Create example list
+example_list = [["example/"+example] for example in os.listdir("examples")]
+
+
+# Create the Graio demo
+demo = gr.Interface(fn=predict, # maps inputs to ouputs
+                    inputs=gr.Image(type="pil"),
+                    outputs=[gr.Label(num_top_classes=3,label='Predictions'),
+                            gr.Number(label="Predicition time (s)")],
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article
+                    )
+
+# Launch the demo!
+demo.launch(debug=False,
+            share=True)

model.py

@@ -0,0 +1,35 @@
+
+
+import torch
+import torchvision
+from torch import nn
+
+def create_effnetb2_model(num_classes:int=3,
+                          seed:int=42):
+
+  
+
+   # 1. Setup  pretrained EffNetB2 weights
+  effnetb2_weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+
+  # 2. Get EffNetB2 transforms
+  effnetb2_transforms = effnetb2_weights.transforms()
+
+  # 3. Setup pretrained model instance
+  effnetb2 = torchvision.models.efficientnet_b2(weights=effnetb2_weights)
+
+  # Set seeds
+  torch.manual_seed(seed=seed)
+
+  # 4. Freeze the base layer in the model (this will stop all layers form training)
+  for params in effnetb2.parameters():
+    params.requires_grad = False
+
+  # 5. Chage the output layer (or header layer) classifier
+  effnetb2.classifier = nn.Sequential(
+    nn.Dropout(p=0.3, inplace=True),
+    nn.Linear(in_features=1408,
+              out_features=num_classes,
+              bias=True)
+  )
+  return effnetb2, effnetb2_transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.5.0
+torchvision==0.20.0
+gradio==5.6.0