Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Improve training messages #8

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Improve training messages #8

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7208680
Remove unnecessary tf.flags string
GabrielMajeri Aug 10, 2019
ba95d11
Improve report messages
GabrielMajeri Aug 10, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 9 additions & 11 deletions nncompress/embed_compress.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,6 @@
else:
from tensorflow.python.ops.rnn_cell_impl import _linear



tf.flags.DEFINE_string('qmats', "data/glove.6B.300d.quant.npy", "output")


class EmbeddingCompressor(object):

_TAU = 1.0
Expand Down Expand Up @@ -200,12 +195,15 @@ def train(self, embed_matrix, max_epochs=200):
report_token = "*"
best_loss = valid_loss
saver.save(sess, self._model_path)
print("[epoch{}] trian_loss={:.2f} train_maxp={:.2f} valid_loss={:.2f} valid_maxp={:.2f} bps={:.0f} {}".format(
epoch,
np.mean(train_loss_list), np.mean(train_maxp_list),
np.mean(valid_loss_list), np.mean(valid_maxp_list),
len(train_loss_list) / time_elapsed,
report_token
print("[Epoch {}/{}] Train loss={:.4f} Train maxp={:.4f}".format(
epoch, max_epochs,
np.mean(train_loss_list), np.mean(train_maxp_list)
))
print("\tValidation loss={:.4f} Validation maxp={:.4f}".format(
np.mean(valid_loss_list), np.mean(valid_maxp_list)
))
print("\tBatches per second={:.0f} {}".format(
len(train_loss_list) / time_elapsed, report_token
))
print("Training Done")

Expand Down