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
+09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.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 sha256:1cb101f9ff531f307470f23ce7b8a94c4dd949bb181985f8102ffaebf52506ae
+size 31314554

app.py

@@ -0,0 +1,57 @@
+### 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 name
+class_names = ["pizza", "steak", "sushi"] 
+
+#creat a model and model_transformation
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=len(class_names))
+
+#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"),
+    )
+)
+
+#prediction fn
+def predict(img) -> Tuple[Dict, float]:
+  start_time = timer()
+
+  img = effnetb2_transforms(img).unsqueeze(0)
+
+  effnetb2.eval()
+  with torch.inference_mode():
+    pred_probs = torch.softmax(effnetb2(img), dim=1)
+  
+  #gradio recieve result in dict
+  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, 5)
+    
+  return pred_labels_and_probs, pred_time
+
+# gradio app
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food as pizza, steak or sushi."
+
+#example list
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+demo = gr.Interface(fn=predict,
+             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)
+
+demo.lunch()

model.py

@@ -0,0 +1,34 @@
+import torch
+import torchvision
+
+from torch import nn
+
+
+def create_effnetb2_model(num_classes:int=3):
+    """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 
+    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==2.3.0
+torchvision==0.18.0
+gradio==4.37.2