Refactor val cadence

scripts/train_bm4dnet.py

@@ -141,7 +141,7 @@ def train(train_cache_dir, val_cache_dir):
     use_amp = False
     use_amp_validation = False
     # Validate (and consider a checkpoint) after every full-cache epoch.
-    val_every = 1
+    val_every = 1000
     seed = 42
 
     # Signal-preserving loss + target/sampling (Parts E/F). preserve_foreground

src/aind_exaspim_image_compression/machine_learning/data_handling.py

@@ -19,6 +19,7 @@
 
 import logging
 import fastremap
+import math
 import numpy as np
 import os
 import queue
@@ -77,6 +78,8 @@ def build_training_example(
         transform.forward(target),
         fg.astype(np.float32),
     )
+
+
 from aind_exaspim_image_compression.utils.swc_util import Reader
 
 
@@ -1312,6 +1315,9 @@ def _load_batch(self, executor, indices):
                 batched[j][i, 0, ...] = field
         return tuple(to_tensor(arr) for arr in batched)
 
+    def __len__(self):
+        return math.ceil(len(self.dataset) / self.batch_size)
+
 
 # --- Helpers ---
 def init_datasets(