Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/bourdakos1/capsule-networks
/ functions
Functions
27 in github.com/bourdakos1/capsule-networks
⨍
Functions
27
◇
Types & classes
2
↓ 8 callers
Function
download_and_uncompress_zip
Args: URL: the download links for data dataset_dir: the path to save data force: re-download data
download_data.py:22
↓ 3 callers
Method
build_arch
(self)
capsNet.py:41
↓ 3 callers
Function
load_mnist
(batch_size, is_training=True)
utils.py:7
↓ 3 callers
Function
squash
Squashing function corresponding to Eq. 1 Args: vector: A tensor with shape [batch_size, 1, num_caps, vec_len, 1] or [batch_size, num_caps
capsLayer.py:176
↓ 2 callers
Function
load_data
(dataset, batch_size, is_training=True, one_hot=False)
utils.py:75
↓ 2 callers
Function
load_fashion_mnist
(batch_size, is_training=True)
utils.py:41
↓ 2 callers
Method
loss
(self)
capsNet.py:104
↓ 2 callers
Function
save_to
()
main.py:12
↓ 1 callers
Method
_summary
(self)
capsNet.py:139
↓ 1 callers
Function
average_gradients
Calculate the average gradient for each shared variable across all towers. Note that this function provides a synchronization point across all towe
dist_version/distributed_train.py:41
↓ 1 callers
Function
create_inputs
()
dist_version/distributed_train.py:16
↓ 1 callers
Function
evaluation
(model, supervisor, num_label)
main.py:93
↓ 1 callers
Function
get_batch_data
(dataset, batch_size, num_threads)
utils.py:84
↓ 1 callers
Function
mergeImgs
(images, size)
utils.py:110
↓ 1 callers
Function
routing
The routing algorithm. Args: input: A Tensor with [batch_size, num_caps_l=1152, 1, length(u_i)=8, 1] shape, num_caps_l me
capsLayer.py:99
↓ 1 callers
Function
start_download
(dataset, save_to, force)
download_data.py:54
↓ 1 callers
Function
tower_loss
(x, y, scope, reuse_variables=None)
dist_version/distributed_train.py:29
↓ 1 callers
Function
train
(model, supervisor, num_label)
main.py:43
Method
__call__
The parameters 'kernel_size' and 'stride' will be used while 'layer_type' equal 'CONV'
capsLayer.py:36
Method
__init__
(self, num_outputs, vec_len, with_routing=True, layer_type='FC')
capsLayer.py:30
Method
__init__
(self, is_training=True)
capsNet.py:18
Function
build_arch
(input, y, is_train=False)
dist_version/capsnet_slim.py:6
Function
download_progress
(count, block_size, total_size)
download_data.py:35
Function
loss
(v_len, output, x, y)
dist_version/capsnet_slim.py:76
Function
main
(_)
main.py:112
Function
main
(_)
dist_version/distributed_train.py:78
Function
save_images
Args: imgs: [batch_size, image_height, image_width] size: a list with tow int elements, [image_height, image_width] path:
utils.py:99