Skip to content

Doc Change: Change in shape for CIFAR Datasets #11043

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

Merged
merged 2 commits into from
Aug 31, 2018
Merged

Doc Change: Change in shape for CIFAR Datasets #11043

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
69af4be
Doc Change: Change in shape for CIFAR Datasets
sriyogesh94 Aug 31, 2018
16fbc40
Doc change added information on the shape of CIFAR datasets
sriyogesh94 Aug 31, 2018
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
Next Next commit
Doc Change: Change in shape for CIFAR Datasets 
Both the CIFAR datasets have been updates now having the channel as the last dimension in the shape resulting in (num_samples, 32, 32, 3)
  • Loading branch information
@sriyogesh94
sriyogesh94 authored Aug 31, 2018
commit 69af4be38559d2c19e3e841df30f3718cd2e4ae8
6 changes: 3 additions & 3 deletions docs/templates/datasets.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ from keras.datasets import cifar10

- __Returns:__
- 2 tuples:
- __x_train, x_test__: uint8 array of RGB image data with shape (num_samples, 3, 32, 32).
- __x_train, x_test__: uint8 array of RGB image data with shape (num_samples, 32, 32, 3).
Copy link
Collaborator

@fchollet fchollet Aug 31, 2018

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is incorrect, the shape depends on your image_data_format settings

Copy link
Contributor Author

@sriyogesh94 sriyogesh94 Aug 31, 2018

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oh! thanks a lot! Your book was fantastic!

- __y_train, y_test__: uint8 array of category labels (integers in range 0-9) with shape (num_samples,).


Expand All @@ -34,7 +34,7 @@ from keras.datasets import cifar100

- __Returns:__
- 2 tuples:
- __x_train, x_test__: uint8 array of RGB image data with shape (num_samples, 3, 32, 32).
- __x_train, x_test__: uint8 array of RGB image data with shape (num_samples, 32, 32, 3).
- __y_train, y_test__: uint8 array of category labels with shape (num_samples,).

- __Arguments:__
Expand Down Expand Up @@ -206,4 +206,4 @@ from keras.datasets import boston_housing
- __test_split__: fraction of the data to reserve as test set.

- __Returns:__
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.