Skip to content

problems in "densenet" and "nmt_with_attention" #492

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

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

problems in "densenet" and "nmt_with_attention" #492

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e010705
Update densenet.py
6eanut Jun 12, 2024
5dbf971
Update train.py
6eanut Jun 12, 2024
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
2 changes: 1 addition & 1 deletion tensorflow_examples/models/densenet/densenet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,7 +188,7 @@ def __init__(self, num_filters, data_format,
data_format=data_format,
kernel_initializer="he_normal",
kernel_regularizer=l2(weight_decay))
self.avg_pool = tf.keras.layers.AveragePooling2D(data_format=data_format)
self.avg_pool = tf.keras.layers.AveragePooling2D(pool_size(2,2),data_format=data_format)

def call(self, x, training=True):
output = self.batchnorm(x, training=training)
Expand Down
4 changes: 2 additions & 2 deletions tensorflow_examples/models/nmt_with_attention/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,8 +154,8 @@ def training_loop(self, train_ds, test_ds):
template = 'Epoch: {}, Train Loss: {}, Test Loss: {}'

for epoch in range(self.epochs):
self.train_loss_metric.reset_states()
self.test_loss_metric.reset_states()
self.train_loss_metric.reset_state()
self.test_loss_metric.reset_state()

for inp, targ in train_ds:
self.train_step((inp, targ))
Expand Down