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.pt filter=lfs diff=lfs merge=lfs -text

09_pretrained_effnetb2_feature_extractor_pizza_steak_sushi_20_percent.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b4f3a85a9b4b8c4a7eae79f59747344f8824ca043f4585a2451d951b024e18
+size 31314554

app.py

@@ -0,0 +1,52 @@
+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.pt",
+        map_location=torch.device('cpu'),
+    )
+)
+
+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)
+
+    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
+
+title = "FoodVision Mini"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images of food."
+article = "Created at pytorch tutorial."
+
+example_list = [["examples/" + example] for example in os.listdir("examples")]
+
+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.launch()

model.py

@@ -0,0 +1,32 @@
+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, default 42
+
+    Returns:
+        model (torch.nn.Module): EffNetB2 feature extractor model.
+        transforms (torchvision.transforms): EffNetB2 image transforms.
+    """
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights)
+
+    for param in model.parameters():
+        param.requires_grad = False
+
+    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 +1,4 @@
+torch==2.4.1
+torchvision==0.19.1
+gradio==4.44.0
+httpx==0.24.1