intial 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
+pretrained_effnetb2_pizza_steak_sushi_20_percent.pt filter=lfs diff=lfs merge=lfs -text
+.pt filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,45 @@
+
+import os
+import torch
+import gradio as gr
+
+from model import create_effnetb2_model
+from timeit import default_timer as timer
+from typing import List, Dict, Tuple
+
+class_names = ["pizza", "steak", "sushi"]
+
+effnetb2, effnetb2_transforms = create_effnetb2_model(num_classes=len(class_names))
+
+effnetb2.load_state_dict(torch.load(f="pretrained_effnetb2_pizza_steak_sushi_20_percent.pt"),
+                         map_location=torch.device("cpu")) # Load model to the CPU
+
+def predict(img) -> Tuple[Dict, float]:
+    start_time = timer()
+
+    img = effnetb2_transform(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))}
+
+    end_time = timer()
+
+    return pred_labels_and_probs, round(end_time-start_time, 4)
+
+title = "FoodVision Mini"
+description = "An [EfficientNetB2 feature extractor](www.google.com) computer vision model to classify images as pizza, steak, sushi"
+
+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)
+
+demo.launch(debug=False)

model.py

@@ -0,0 +1,21 @@
+
+import torch
+import torchvision
+from torch import nn
+
+def create_effnetb2_model(num_classes: int = 3,
+                          seed: int = 42):
+    weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = weights.transforms()
+    model = torchvision.models.efficientnet_b2(weights=weights).to(device)
+
+    for param in model.parameters():
+        param.requires_grad = False
+
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed(seed)
+    model.classifier = nn.Sequential(
+        nn.Dropout(p=0.3, inplace=True),
+        nn.Linear(in_features=1408, out_features=num_classes, bias=True)
+    ).to(device)
+    return model, transforms

pretrained_effnetb2_pizza_steak_sushi_20_percent.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05fec3d6ac9082ddfed66b4ed747ddaf4779e21b50186dd6636ceb13168528b0
+size 31299161

requirements.txt

@@ -0,0 +1,4 @@
+
+torch==2.9.0
+torchvision==0.24.0
+gradio==6.0.0