Update documentation for CIFAR datasets.
This commit is contained in:
parent
28113b2010
commit
39a69b3f52
@ -4,12 +4,12 @@
|
|||||||
|
|
||||||
`keras.datasets.cifar10`
|
`keras.datasets.cifar10`
|
||||||
|
|
||||||
Dataset of 50,000 32x32 color images, labeled over 10 categories.
|
Dataset of 50,000 32x32 color training images, labeled over 10 categories, and 10,000 test images.
|
||||||
|
|
||||||
### Usage:
|
### Usage:
|
||||||
|
|
||||||
```python
|
```python
|
||||||
(X_train, y_train), (X_test, y_test) = cifar10.load_data(test_split=0.1, seed=113)
|
(X_train, y_train), (X_test, y_test) = cifar10.load_data()
|
||||||
```
|
```
|
||||||
|
|
||||||
- __Return:__
|
- __Return:__
|
||||||
@ -17,10 +17,28 @@ Dataset of 50,000 32x32 color images, labeled over 10 categories.
|
|||||||
- __X_train, X_test__: uint8 array of RGB image data with shape (nb_samples, 3, 32, 32).
|
- __X_train, X_test__: uint8 array of RGB image data with shape (nb_samples, 3, 32, 32).
|
||||||
- __y_train, y_test__: uint8 array of category labels (integers in range 0-9) with shape (nb_samples,).
|
- __y_train, y_test__: uint8 array of category labels (integers in range 0-9) with shape (nb_samples,).
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## CIFAR100 small image classification
|
||||||
|
|
||||||
|
`keras.datasets.cifar100`
|
||||||
|
|
||||||
|
Dataset of 50,000 32x32 color training images, labeled over 100 categories, and 10,000 test images.
|
||||||
|
|
||||||
|
### Usage:
|
||||||
|
|
||||||
|
```python
|
||||||
|
(X_train, y_train), (X_test, y_test) = cifar100.load_data(label_mode='fine')
|
||||||
|
```
|
||||||
|
|
||||||
|
- __Return:__
|
||||||
|
- 2 tuples:
|
||||||
|
- __X_train, X_test__: uint8 array of RGB image data with shape (nb_samples, 3, 32, 32).
|
||||||
|
- __y_train, y_test__: uint8 array of category labels with shape (nb_samples,).
|
||||||
|
|
||||||
- __Arguments:__
|
- __Arguments:__
|
||||||
|
|
||||||
- __test_split__: float. Fraction of the dataset to be used as test data.
|
- __label_mode__: "fine" or "coarse".
|
||||||
- __seed__: int. Seed for reproducible data shuffling.
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
@ -29,7 +29,7 @@ nb_epoch = 200
|
|||||||
data_augmentation = True
|
data_augmentation = True
|
||||||
|
|
||||||
# the data, shuffled and split between tran and test sets
|
# the data, shuffled and split between tran and test sets
|
||||||
(X_train, y_train), (X_test, y_test) = cifar10.load_data(test_split=0.1)
|
(X_train, y_train), (X_test, y_test) = cifar10.load_data()
|
||||||
print(X_train.shape[0], 'train samples')
|
print(X_train.shape[0], 'train samples')
|
||||||
print(X_test.shape[0], 'test samples')
|
print(X_test.shape[0], 'test samples')
|
||||||
|
|
||||||
|
Loading…
Reference in New Issue
Block a user