Upload 2 files

convt_gem.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659d9727679573903df66d7fb516123bbce1b2c3c6f3391c67de0562b573b29a
+size 131377527

script.py

@@ -0,0 +1,97 @@
+import pandas as pd
+import numpy as np
+from PIL import Image
+import onnxruntime as ort
+import os
+from tqdm import tqdm
+
+
+def is_gpu_available():
+    """Check if the python package `onnxruntime-gpu` is installed."""
+    return ort.get_device() == "GPU"
+
+
+class ONNXWorker:
+    """Run inference using ONNX runtime."""
+
+    def __init__(self, onnx_path: str):
+        print("Setting up ONNX runtime session.")
+        self.use_gpu = is_gpu_available()
+        if self.use_gpu:
+            providers = ["CUDAExecutionProvider", "CPUExecutionProvider"]
+        else:
+            providers = ["CPUExecutionProvider"]
+
+        print(f"Using {providers}")
+        self.ort_session = ort.InferenceSession(onnx_path, providers=providers)
+
+    def _resize_image(self, image: np.ndarray) -> np.ndarray:
+        """
+
+        :param image:
+        :return:
+        """
+
+        newsize = (300, 300)
+        im1 = im1.resize(newsize)
+
+    def predict_image(self, image: np.ndarray) -> list():
+        """Run inference using ONNX runtime.
+
+        :param image: Input image as numpy array.
+        :return: A list with logits and confidences.
+        """
+
+        logits= self.ort_session.run(None, {"input": image.astype(dtype=np.float32)})
+
+        return logits
+
+
+def make_submission(test_metadata, model_path, output_csv_path="./submission.csv", images_root_path="/tmp/data/private_testset"):
+    """Make submission with given """
+
+    model = ONNXWorker(model_path)
+
+    predictions = []
+
+    for _, row in tqdm(test_metadata.iterrows(), total=len(test_metadata)):
+        image_path = os.path.join(images_root_path, row.image_path)
+
+        test_image = Image.open(image_path).convert("RGB")
+        test_image_resized = np.asarray(test_image.resize((256, 256)))
+        mean=np.array([0.485, 0.456, 0.406])
+        std=np.array([0.229, 0.224, 0.225])
+        mean=mean[None,None,:]
+        std=std[None,None,:]
+        test_image_resized=test_image_resized/255
+        test_image_resized=(test_image_resized-mean)/std
+        test_image_resized=test_image_resized.astype(np.float32)
+        test_image_resized=test_image_resized[None,:,:,:].transpose(0,3,1,2)
+        
+
+        logits = model.predict_image(test_image_resized)[0]
+
+        predictions.append(np.argmax(logits))
+
+    test_metadata["class_id"] = predictions
+
+    user_pred_df = test_metadata.drop_duplicates("observation_id", keep="first")
+    user_pred_df[["observation_id", "class_id"]].to_csv(output_csv_path, index=None)
+
+
+if __name__ == "__main__":
+
+    import zipfile
+
+    with zipfile.ZipFile("/tmp/data/private_testset.zip", 'r') as zip_ref:
+        zip_ref.extractall("/tmp/data")
+
+    ONNX_MODEL_PATH = "./convt_gem.onnx"
+
+    metadata_file_path = "SnakeCLEF2024-TestMetadata.csv"
+    test_metadata = pd.read_csv(metadata_file_path)
+
+    make_submission(
+        test_metadata=test_metadata,
+        model_path=ONNX_MODEL_PATH,
+    )