scripts to validate and test

python/test_image.py

@@ -0,0 +1,19 @@
+import onnxruntime as ort
+from PIL import Image
+import numpy as np
+
+# Load the ONNX model
+session = ort.InferenceSession('./saved-model/model.onnx')
+
+# Get input and output names
+input_name = session.get_inputs()[0].name
+output_name = session.get_outputs()[0].name
+
+# Load and preprocess the image
+img = Image.open('./training_images/shirt/00e745c9-97d9-429d-8c3f-d3db7a2d2991.jpg').resize((128, 128))
+img_array = np.array(img).astype(np.float32) / 255.0  # Normalize pixel values to [0, 1]
+img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+
+# Run inference
+outputs = session.run([output_name], {input_name: img_array})
+print(f"Inference outputs: {outputs}")

python/verify_onnx_model.py

@@ -0,0 +1,31 @@
+import onnxruntime as ort
+import numpy as np
+
+def verify_onnx_model(onnx_model_path):
+    # Load the ONNX model
+    onnx_session = ort.InferenceSession(onnx_model_path)
+
+    # Display model input details
+    input_name = onnx_session.get_inputs()[0].name
+    input_shape = onnx_session.get_inputs()[0].shape
+    input_type = onnx_session.get_inputs()[0].type
+    print(f"Input Name: {input_name}, Shape: {input_shape}, Type: {input_type}")
+
+    # Display model output details
+    output_name = onnx_session.get_outputs()[0].name
+    output_shape = onnx_session.get_outputs()[0].shape
+    output_type = onnx_session.get_outputs()[0].type
+    print(f"Output Name: {output_name}, Shape: {output_shape}, Type: {output_type}")
+
+    # Generate a dummy input matching the input shape
+    # Assuming input shape is [None, 128, 128, 3], where None is the batch size
+    dummy_input = np.random.rand(1, 128, 128, 3).astype(np.float32)
+
+    # Perform inference
+    result = onnx_session.run([output_name], {input_name: dummy_input})
+    print(f"Inference Result: {result}")
+
+# Path to the ONNX model
+onnx_model_path = './model.onnx'
+
+verify_onnx_model(onnx_model_path)