Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
ResNet50_tensorflow
Commits
a8a03c80
Commit
a8a03c80
authored
May 12, 2016
by
Vincent Li
Browse files
Typos
parent
32ab5a58
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
inception/inception/image_processing.py
inception/inception/image_processing.py
+2
-2
No files found.
inception/inception/image_processing.py
View file @
a8a03c80
...
@@ -15,7 +15,7 @@
...
@@ -15,7 +15,7 @@
"""Read and preprocess image data.
"""Read and preprocess image data.
Image processing occurs on a single image at a time. Image are read and
Image processing occurs on a single image at a time. Image are read and
preprocessed in para
r
llel across mul
i
tple threads. The resulting images
preprocessed in parallel across mult
i
ple threads. The resulting images
are concatenated together to form a single batch for training or evaluation.
are concatenated together to form a single batch for training or evaluation.
-- Provide processed image data for a network:
-- Provide processed image data for a network:
...
@@ -54,7 +54,7 @@ tf.app.flags.DEFINE_integer('num_preprocess_threads', 4,
...
@@ -54,7 +54,7 @@ tf.app.flags.DEFINE_integer('num_preprocess_threads', 4,
tf
.
app
.
flags
.
DEFINE_integer
(
'num_readers'
,
4
,
tf
.
app
.
flags
.
DEFINE_integer
(
'num_readers'
,
4
,
"""Number of parallel readers during train."""
)
"""Number of parallel readers during train."""
)
# Images are preprocessed asynchronously using multiple threads specifed by
# Images are preprocessed asynchronously using multiple threads specif
i
ed by
# --num_preprocss_threads and the resulting processed images are stored in a
# --num_preprocss_threads and the resulting processed images are stored in a
# random shuffling queue. The shuffling queue dequeues --batch_size images
# random shuffling queue. The shuffling queue dequeues --batch_size images
# for processing on a given Inception tower. A larger shuffling queue guarantees
# for processing on a given Inception tower. A larger shuffling queue guarantees
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment