Closed StephenChan closed 6 months ago
As seen in train_utils.py's train() function (link), the mini-batch size (and reference-set size cap) is determined as follows:
train()
# Calculate max nbr images to keep in memory (for 5000 samples total). max_imgs_in_memory = 5000 // labels.samples_per_image
Better to base this on a customizable number instead of a hardcoded 5000.
Done in PR #71. Now controlled by the config var TRAINING_BATCH_LABEL_COUNT.
TRAINING_BATCH_LABEL_COUNT
As seen in train_utils.py's
train()
function (link), the mini-batch size (and reference-set size cap) is determined as follows:Better to base this on a customizable number instead of a hardcoded 5000.