initial 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_effnetb2_sushi_steak_pizza_20.pth filter=lfs diff=lfs merge=lfs -text

09_effnetb2_sushi_steak_pizza_20.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1089e94d426a33e77384b11f0af45279e289b7ccd747c968f8efbf026aaf8885
+size 31287545

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+import os
+import torch
+
+from model import create_effnetb2_model
+from timeit import default_timer as timer
+
+# Setup class names
+class_names = ["pizza", "steak", "sushi"]
+
+# Model and transforms
+effnetb2, effnetb2_transforms = create_effnetb2_model(
+    num_classes=3,
+)
+
+# Load saved weights
+effnetb2.load_state_dict(
+    torch.load(f="09_effnetb2_sushi_steak_pizza_20.pth", map_location=("cpu")) # load the model to the CPU
+)
+
+# prediction function
+def predict(img) -> tuple:
+    start_time = timer()
+    img = effnetb2_transforms(img).unsqueeze(0)
+    effnetb2.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(effnetb2(img), dim=1)
+
+    pred_labesl_and_probs = {
+        class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))
+    }
+    end_time = timer()
+    pred_time = round(end_time - start_time, 4)
+    return pred_labesl_and_probs, pred_time
+
+
+# gradio app
+title = "FoodVision Mini 🍕🥩🍣"
+description = "An EfficientNetB2 feature extractor computer vision model to classify images as pizza, steak, sushi."
+article = "Created at 09 PyTorch Model Deployment."
+
+# create example list
+foodvision_min_examples_path = "examples"
+example_list = [
+    [os.path.join(foodvision_min_examples_path, file)]
+    for file in os.listdir(foodvision_min_examples_path)
+    if file.lower().endswith((".jpg", ".jpeg", ".png"))
+]
+
+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)")],
+    title=title,
+    description=description,
+    article=article,
+    examples=example_list
+)
+demo.launch(share=False, server_name="0.0.0.0", debug=False)

model.py

@@ -0,0 +1,21 @@
+import torchvision
+from torch import nn
+
+
+def create_effnetb2_model(num_classes: int = 3):
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    # Get EffNetB2 transforms
+    transforms = weights.transforms()
+
+    # Setup pretrained model instance
+    model = torchvision.models.efficientnet_b2(weights=weights)
+
+    # Freeze the base layers in the model ( this will stop all layers from training)
+    for param in model.parameters():
+        param.requires_grad = False
+
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes, bias=True),
+    )
+    return model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch==2.11.0
+torchvision==0.26.0
+gradio==6.12.0