Commit 4efaddb6 authored by T.H.C. Heshan's avatar T.H.C. Heshan

Update model.py

parent 3835901e
...@@ -57,8 +57,7 @@ train_ds = train_ds.map(squeeze, tf.data.AUTOTUNE) ...@@ -57,8 +57,7 @@ train_ds = train_ds.map(squeeze, tf.data.AUTOTUNE)
val_ds = val_ds.map(squeeze, tf.data.AUTOTUNE) val_ds = val_ds.map(squeeze, tf.data.AUTOTUNE)
#The `utils.audio_dataset_from_directory` function only returns up to two splits. It's a good idea to keep a test set separate from your validation set. #use `Dataset.shard` to split the validation set into two halves.
#Ideally you'd keep it in a separate directory, but in this case you can use `Dataset.shard` to split the validation set into two halves. Note that iterating over **any** shard will load **all** the data, and only keep its fraction.
test_ds = val_ds.shard(num_shards=2, index=0) test_ds = val_ds.shard(num_shards=2, index=0)
val_ds = val_ds.shard(num_shards=2, index=1) val_ds = val_ds.shard(num_shards=2, index=1)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment