Skip to content

F
ffm-baseline
Commit 09360156 authored by 张彦钊's avatar 张彦钊
Browse files
Options

把训练时l2正则化改成l1正则化

parent e5702665
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 1 deletion
eda/esmm/Model_pipline/train.py
View file @ 09360156
...@@ -71,7 +71,6 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False): ...@@ -71,7 +71,6 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
# Extract lines from input files using the Dataset API, can pass one filename or filename list # Extract lines from input files using the Dataset API, can pass one filename or filename list
# dataset = tf.data.TFRecordDataset(filenames).map(_parse_fn, num_parallel_calls=8).prefetch(500000) # multi-thread pre-process then prefetch # dataset = tf.data.TFRecordDataset(filenames).map(_parse_fn, num_parallel_calls=8).prefetch(500000) # multi-thread pre-process then prefetch
# Randomizes input using a window of 256 elements (read into memory) # Randomizes input using a window of 256 elements (read into memory)
# if perform_shuffle: # if perform_shuffle:
# dataset = dataset.shuffle(buffer_size=256) # dataset = dataset.shuffle(buffer_size=256)
......
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