Upload 7 files

README.md

@@ -0,0 +1,3 @@
+---
+license: mit
+---

best_accuracy_BCE_CE.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d05a3823ff0104619dfc17a79ef1a28a99f185ef2034257e7977778c881c4a6
+size 115896262

main.py

@@ -0,0 +1,101 @@
+import pandas as pd
+import numpy as np
+import onnxruntime as ort
+import os
+from tqdm import tqdm
+import timm
+import torchvision.transforms as T
+from PIL import Image
+import torch
+
+def is_gpu_available():
+    """Check if the python package `onnxruntime-gpu` is installed."""
+    return torch.cuda.is_available()
+
+
+class PytorchWorker:
+    """Run inference using ONNX runtime."""
+
+    def __init__(self, model_path: str, model_name: str, number_of_categories: int = 1784):
+
+        def _load_model(model_name, model_path):
+
+            print("Setting up Pytorch Model")
+            self.device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+            print(f"Using devide: {self.device}")
+
+            model = timm.create_model(model_name, num_classes=number_of_categories, pretrained=False)
+
+            # if not torch.cuda.is_available():
+            #     model_ckpt = torch.load(model_path, map_location=torch.device("cpu"))
+            # else:
+            #     model_ckpt = torch.load(model_path)
+
+            model_ckpt = torch.load(model_path, map_location=self.device)
+            model.load_state_dict(model_ckpt)
+
+            return model.to(self.device).eval()
+
+        self.model = _load_model(model_name, model_path)
+
+        self.transforms = T.Compose([T.Resize((256, 256)),
+                                     T.ToTensor(),
+                                     T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
+
+
+    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.model(self.transforms(image).unsqueeze(0).to(self.device))
+
+        return logits.tolist()
+
+
+def make_submission(test_metadata, model_path, model_name, output_csv_path="./submission.csv", images_root_path="/tmp/data/private_testset"):
+    """Make submission with given """
+
+    model = PytorchWorker(model_path, model_name)
+
+    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")
+
+        logits = model.predict_image(test_image)
+
+        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")
+
+    # MODEL_PATH = "pytorch_model.bin"
+    MODEL_PATH = "best_accuracy.pth"
+    # MODEL_NAME = "tf_efficientnet_b1.ap_in1k"
+    MODEL_NAME = "swinv2_tiny_window16_256.ms_in1k"
+
+    metadata_file_path = "./FungiCLEF2024_TestMetadata.csv"
+    # metadata_file_path = "/home/zeleznyt/mnt/data-ntis/projects/korpusy_cv/SnakeCLEF2024/SnakeCLEF2023-ValMetadata.csv"
+    test_metadata = pd.read_csv(metadata_file_path)
+
+    make_submission(
+        test_metadata=test_metadata,
+        model_path=MODEL_PATH,
+        model_name=MODEL_NAME,
+        # images_root_path='/home/zeleznyt/mnt/data-ntis/projects/korpusy_cv/SnakeCLEF2024/val/SnakeCLEF2023-medium_size'
+    )

script.py

@@ -0,0 +1,113 @@
+import pandas as pd
+import numpy as np
+from torch import nn
+import os
+from tqdm import tqdm
+import timm
+import torchvision.transforms as T
+from PIL import Image
+import torch
+
+def is_gpu_available():
+    """Check if the python package `onnxruntime-gpu` is installed."""
+    return torch.cuda.is_available()
+
+class CustomModel(nn.Module):
+    def __init__(self, base_model_name, num_classes1, num_classes2):
+        super(CustomModel, self).__init__()
+        self.base_model = timm.create_model(base_model_name, pretrained=False)
+        in_features = self.base_model.get_classifier().in_features
+        self.base_model.reset_classifier(0)  # Remove the original classification layer
+
+        self.fc1 = nn.Linear(in_features, num_classes1)  # Binary classification output
+        self.fc2 = nn.Linear(in_features, num_classes2)  # Categorical classification output
+
+    def forward(self, x):
+        x = self.base_model(x)
+        out1 = torch.sigmoid(self.fc1(x))  # Binary output
+        out2 = self.fc2(x)  # Categorical output
+        return out2
+
+class PytorchWorker:
+    """Run inference using ONNX runtime."""
+
+    def __init__(self, model_path: str, model_name: str, number_of_categories: int = 1784):
+
+        def _load_model(model_name, model_path):
+
+            print("Setting up Pytorch Model")
+            self.device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+            print(f"Using devide: {self.device}")
+
+            model = CustomModel(model_name, 1, number_of_categories)
+
+            # if not torch.cuda.is_available():
+            #     model_ckpt = torch.load(model_path, map_location=torch.device("cpu"))
+            # else:
+            #     model_ckpt = torch.load(model_path)
+
+            model_ckpt = torch.load(model_path, map_location=self.device)
+            model.load_state_dict(model_ckpt)
+
+            return model.to(self.device).eval()
+
+        self.model = _load_model(model_name, model_path)
+
+        self.transforms = T.Compose([T.Resize((256, 256)),
+                                     T.ToTensor(),
+                                     T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
+
+
+    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.model(self.transforms(image).unsqueeze(0).to(self.device))
+
+        return logits.tolist()
+
+
+def make_submission(test_metadata, model_path, model_name, output_csv_path="./submission.csv", images_root_path="/tmp/data/private_testset"):
+    """Make submission with given """
+
+    model = PytorchWorker(model_path, model_name)
+
+    predictions = []
+
+    for _, row in tqdm(test_metadata.iterrows(), total=len(test_metadata)):
+        image_path = os.path.join(images_root_path, row.filename)
+
+        test_image = Image.open(image_path).convert("RGB")
+
+        logits = model.predict_image(test_image)
+
+        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")
+
+    MODEL_PATH = "best_accuracy_BCE_CE.pth"
+    MODEL_NAME = "swinv2_tiny_window16_256.ms_in1k"
+
+    metadata_file_path = "./SnakeCLEF2024-TestMetadata.csv"
+    test_metadata = pd.read_csv(metadata_file_path)
+
+    make_submission(
+        test_metadata=test_metadata,
+        model_path=MODEL_PATH,
+        model_name=MODEL_NAME,
+        # images_root_path='/home/zeleznyt/mnt/data-ntis/projects/korpusy_cv/SnakeCLEF2024/val/SnakeCLEF2023-medium_size'
+    )

swinv2_tiny_window16_256.ms_in1k.yaml

@@ -0,0 +1,23 @@
+# data
+augmentations: 'vit_heavy'
+image_size: [256, 256]  # [height, width]
+dataset: 'SnakeCLEF2023'
+
+# model
+architecture: 'swinv2_tiny_window16_256.ms_in1k'
+
+# training
+loss: 'SeeSawLoss'
+optimizer: 'SGD'
+scheduler: 'plateau'
+epochs: 100
+learning_rate: 0.01
+batch_size: 32
+accumulation_steps: 4
+
+# other
+random_seed: 777
+workers: 1
+multigpu: False
+tags: ["Fine-tuning"]  # W&B Run tags
+root_path: "./"