Create a small version of the Camelyon16 dataset (#667)

* added camelyon16 small * added camelyon16 small
kaiko-ai · Oct 8, 2024 · d8bd3f9 · d8bd3f9
1 parent be6dc72
commit d8bd3f9
Showing 1 changed file with 134 additions and 0 deletions.
diff --git a/configs/vision/pathology/offline/classification/camelyon16_small.yaml b/configs/vision/pathology/offline/classification/camelyon16_small.yaml
@@ -0,0 +1,134 @@
+---
+trainer:
+  class_path: eva.Trainer
+  init_args:
+    n_runs: &N_RUNS ${oc.env:N_RUNS, 5}
+    default_root_dir: &OUTPUT_ROOT ${oc.env:OUTPUT_ROOT, logs/${oc.env:MODEL_NAME, dino_vits16}/offline/camelyon16}
+    max_epochs: &MAX_EPOCHS ${oc.env:MAX_EPOCHS, 100}
+    callbacks:
+      - class_path: eva.callbacks.ConfigurationLogger
+      - class_path: lightning.pytorch.callbacks.TQDMProgressBar
+        init_args:
+          refresh_rate: ${oc.env:TQDM_REFRESH_RATE, 1}
+      - class_path: lightning.pytorch.callbacks.LearningRateMonitor
+        init_args:
+          logging_interval: epoch
+      - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+        init_args:
+          filename: best
+          save_last: true
+          save_top_k: 1
+          monitor: &MONITOR_METRIC ${oc.env:MONITOR_METRIC, val/BinaryAccuracy}
+          mode: &MONITOR_METRIC_MODE ${oc.env:MONITOR_METRIC_MODE, max}
+      - class_path: lightning.pytorch.callbacks.EarlyStopping
+        init_args:
+          min_delta: 0
+          patience: ${oc.env:PATIENCE, 10}
+          monitor: *MONITOR_METRIC
+          mode: *MONITOR_METRIC_MODE
+      - class_path: eva.callbacks.ClassificationEmbeddingsWriter
+        init_args:
+          output_dir: &DATASET_EMBEDDINGS_ROOT ${oc.env:EMBEDDINGS_ROOT, ./data/embeddings/${oc.env:MODEL_NAME, dino_vits16}/camelyon16}
+          save_every_n: 10_000
+          dataloader_idx_map:
+            0: train
+            1: val
+            2: test
+          metadata_keys: ["wsi_id"]
+          backbone:
+            class_path: eva.vision.models.ModelFromRegistry
+            init_args:
+              model_name: ${oc.env:MODEL_NAME, universal/}
+              model_extra_kwargs: ${oc.env:MODEL_EXTRA_KWARGS, null}
+          overwrite: false
+    logger:
+      - class_path: lightning.pytorch.loggers.TensorBoardLogger
+        init_args:
+          save_dir: *OUTPUT_ROOT
+          name: ""
+model:
+  class_path: eva.HeadModule
+  init_args:
+    head:
+      class_path: eva.vision.models.networks.ABMIL
+      init_args:
+        input_size: ${oc.env:IN_FEATURES, 384}
+        output_size: &NUM_CLASSES 1
+        projected_input_size: 128
+    criterion: torch.nn.BCEWithLogitsLoss
+    optimizer:
+      class_path: torch.optim.AdamW
+      init_args:
+        lr: ${oc.env:LR_VALUE, 0.001}
+        betas: [0.9, 0.999]
+    lr_scheduler:
+      class_path: torch.optim.lr_scheduler.CosineAnnealingLR
+      init_args:
+        T_max: *MAX_EPOCHS
+        eta_min: 0.0
+    metrics:
+      common:
+        - class_path: eva.metrics.AverageLoss
+        - class_path: eva.metrics.BinaryClassificationMetrics
+data:
+  class_path: eva.DataModule
+  init_args:
+    datasets:
+      train:
+        class_path: eva.datasets.MultiEmbeddingsClassificationDataset
+        init_args: &DATASET_ARGS
+          root: *DATASET_EMBEDDINGS_ROOT
+          manifest_file: manifest.csv
+          split: train
+          embeddings_transforms:
+            class_path: eva.core.data.transforms.Pad2DTensor
+            init_args:
+              pad_size: &N_PATCHES 500
+          target_transforms:
+            class_path: eva.core.data.transforms.dtype.ArrayToFloatTensor
+      val:
+        class_path: eva.datasets.MultiEmbeddingsClassificationDataset
+        init_args:
+          <<: *DATASET_ARGS
+          split: val
+      test:
+        class_path: eva.datasets.MultiEmbeddingsClassificationDataset
+        init_args:
+          <<: *DATASET_ARGS
+          split: test
+      predict:
+        - class_path: eva.vision.datasets.Camelyon16
+          init_args: &PREDICT_DATASET_ARGS
+            root: ${oc.env:DATA_ROOT, ./data/camelyon16}
+            sampler:
+              class_path: eva.vision.data.wsi.patching.samplers.ForegroundGridSampler
+              init_args:
+                max_samples: *N_PATCHES
+            width: 224
+            height: 224
+            target_mpp: 0.25
+            split: train
+            image_transforms:
+              class_path: eva.vision.data.transforms.common.ResizeAndCrop
+              init_args:
+                size: ${oc.env:RESIZE_DIM, 224} 
+                mean: ${oc.env:NORMALIZE_MEAN, [0.485, 0.456, 0.406]} 
+                std: ${oc.env:NORMALIZE_STD, [0.229, 0.224, 0.225]}
+        - class_path: eva.vision.datasets.Camelyon16
+          init_args:
+            <<: *PREDICT_DATASET_ARGS
+            split: val
+        - class_path: eva.vision.datasets.Camelyon16
+          init_args:
+            <<: *PREDICT_DATASET_ARGS
+            split: test
+    dataloaders:
+      train:
+        batch_size: &BATCH_SIZE ${oc.env:BATCH_SIZE, 32}
+        shuffle: true
+      val:
+        batch_size: *BATCH_SIZE
+      test:
+        batch_size: *BATCH_SIZE
+      predict:
+        batch_size: &PREDICT_BATCH_SIZE ${oc.env:PREDICT_BATCH_SIZE, 64}