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
+airplane_uncompiled.pth filter=lfs diff=lfs merge=lfs -text

airplane_uncompiled.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c3c11a6aba10b22eac86bccabcd23e56bb2a3258f380ba9f6c258b173e4ddb
+size 31356145

airplanes.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14163fcf18a027d04c245c56f525076a26c37799c95a7688c1f4cf2d3f99f19
+size 30536510

app.py

@@ -0,0 +1,51 @@
+import gradio as gr
+import os
+import torch
+
+from model import load_model
+from timeit import default_timer as timer
+from typing import Tuple, Dict
+
+# class names
+class_names = ['A-10', 'C-130', 'F-16']
+
+model, transform = load_model()
+
+# predict function
+def predict(img):
+    
+    start_time = timer()
+    
+    img = transform(img).unsqueeze(0)
+    
+    model.eval()
+    with torch.inference_mode():
+        pred_probs = torch.softmax(model(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()
+        
+        pred_time = round(end_time - start_time, 4)
+        
+        return pred_labels_and_probs, pred_time
+
+    
+    
+title = "Military Aircraft predictor - Efficinet_B2 Computer Vision Model (PyTorch)"
+
+description = "An EfficientNetB2 feature extractor computer vision model to classify Custom Dataset of F-16 Fighter Jet, C-130 Hercules, A-10 Warthog"
+
+article = "Created in SageMaker Studio"    
+
+example_list = [["examples/" + example] for example in os.listdir("examples")] 
+    
+# Gradio app
+demo = gr.Interface(fn=predict,
+                    inputs=gr.Image(type="pil"),
+                    outputs=[gr.Label(num_top_classes=10, label="Predictions"),
+                            gr.Number(label="Prediction time (s)")],
+                    examples=example_list,
+                    title=title,
+                    description=description,
+                    article=article)

model.py

@@ -0,0 +1,11 @@
+import torch
+import torchvision
+from torch import nn
+
+def load_model():
+    
+    loaded_model = torch.load('demo/airplanes/airplane_uncompiled.pth', map_location=torch.device('cpu'))
+    model_weights = torchvision.models.EfficientNet_B2_Weights.DEFAULT
+    transforms = model_weights.transforms()
+    
+    return loaded_model, transforms

requirements.txt

@@ -0,0 +1,3 @@
+torch
+torchvision
+gradio