Functions — github.com/commaai/research

hub / github.com/commaai/research / functions

Functions92 in github.com/commaai/research

⨍ Functions 92 ◇ Types & classes 4

↓ 8 callersMethodget_config

(self)

models/layers.py:111

↓ 4 callersFunctionmake_gif

(images, fname, duration=2, true_image=False)

models/utils.py:132

↓ 4 callersFunctionsave_images

(images, size, image_path, gray=False)

models/utils.py:20

↓ 3 callersMethod__init__

(self, epsilon=1e-5, momentum=0.9, weights=None, beta_init='zero', gamma_init='normal', **kwarg

models/layers.py:130

↓ 3 callersFunctionclient_generator

Generator in client side should extend this generator Parameters ---------- port : int hwm : int, optional The `ZeroMQ high-water mark (HW

server.py:93

↓ 3 callersFunctionload

Load tensorflow model checkpoint

models/utils.py:215

↓ 3 callersFunctionsave

Save tensorflow model checkpoint

models/utils.py:203

↓ 2 callersFunctiondraw_path_on

(img, speed_ms, angle_steers, color=(0,0,255))

view_steering_model.py:81

↓ 2 callersFunctiongen

(hwm, host, port)

train_steering_model.py:15

↓ 2 callersFunctionget_model

(sess, image_shape=(80, 160, 3), gf_dim=64, df_dim=64, batch_size=64, name="transition", gpu=0)

models/transition.py:46

↓ 2 callersFunctionimsave

(images, size, path, gray=False)

models/utils.py:44

↓ 2 callersFunctioninverse_transform

(images)

models/utils.py:65

↓ 2 callersFunctionmerge

(images, size, gray=False)

models/utils.py:29

↓ 1 callersFunctioncalc_curvature

(v_ego, angle_steers, angle_offset=0)

view_steering_model.py:63

↓ 1 callersFunctioncalc_lookahead_offset

(v_ego, angle_steers, d_lookahead, angle_offset=0)

view_steering_model.py:73

↓ 1 callersFunctioncenter_crop

(x, crop_h, crop_w=None, resize_w=64)

models/utils.py:48

↓ 1 callersFunctioncleanup

(data)

models/transition.py:28

↓ 1 callersFunctionconcatenate

(camera_names, time_len)

dask_generator.py:16

↓ 1 callersFunctiondatagen

Parameters: ----------- leads : bool, should we use all x, y and speed radar leads? default is false, uses only x

dask_generator.py:64

↓ 1 callersFunctiondiscriminator

(batch_size, df_dim, ch, rows, cols)

models/autoencoder.py:100

↓ 1 callersFunctiondraw_path

(img, path_x, path_y, color)

view_steering_model.py:57

↓ 1 callersFunctiondraw_pt

(img, x, y, color, sz=1)

view_steering_model.py:51

↓ 1 callersFunctionencoder

(batch_size, df_dim, ch, rows, cols)

models/autoencoder.py:70

↓ 1 callersFunctiongen

(hwm, host, port)

train_generative_model.py:29

↓ 1 callersFunctiongenerator

(batch_size, gf_dim, ch, rows, cols)

models/autoencoder.py:43

↓ 1 callersMethodget_constants

(self, x)

models/layers.py:301

↓ 1 callersMethodget_constants

(self, x)

models/layers.py:504

↓ 1 callersFunctionget_model

(time_len=1)

train_steering_model.py:24

↓ 1 callersMethodget_output_shape_for

(self, input_shape)

models/layers.py:77

↓ 1 callersFunctionimread

(path)

models/utils.py:23

↓ 1 callersFunctionmain

()

ros/dataset_to_rosbag.py:13

↓ 1 callersFunctionperspective_tform

(x, y)

view_steering_model.py:46

↓ 1 callersMethodpreprocess_input

(self, x)

models/layers.py:267

↓ 1 callersMethodpreprocess_input

(self, x)

models/layers.py:469

↓ 1 callersFunctionrecv_arrays

Receive a list of NumPy arrays. Parameters ---------- socket : :class:`zmq.Socket` The socket to receive the arrays on. Returns -------

server.py:57

↓ 1 callersMethodreset_states

(self)

models/layers.py:255

↓ 1 callersMethodreset_states

(self)

models/layers.py:457

↓ 1 callersFunctionsampler

(z, x)

models/transition.py:124

↓ 1 callersFunctionsend_arrays

Send NumPy arrays using the buffer interface and some metadata. Parameters ---------- socket : :class:`zmq.Socket` The socket to send data ov

server.py:21

↓ 1 callersFunctionstart_server

Start a data processing server. This command starts a server in the current process that performs the actual data processing (by retrieving data

server.py:120

↓ 1 callersMethodtrain_bn

(self, x)

models/layers.py:160

↓ 1 callersFunctiontrain_model

Main training loop. modified from Keras fit_generator

train_generative_model.py:35

↓ 1 callersFunctiontransform

(image, npx=64, is_crop=True)

models/utils.py:57

↓ 1 callersFunctiontransition

(batch_size, dim=1000)

models/conditional.py:40

↓ 1 callersFunctiontransition

(batch_size, dim=1000)

models/transition.py:39

Method__init__

(self, nb_filter, nb_row, nb_col, init='glorot_uniform', activation='linear', weights=None,

models/layers.py:11

Method__init__

(self, output_dim, output_length, init='glorot_uniform', inner_init='orthogonal',

models/layers.py:200

Method__init__

(self, output_dim, output_length, control_dim=2, init='glorot_uniform', inner_init='orthogonal'

models/conditional.py:28

Functioncleanup

(data)

models/autoencoder.py:35

models/conditional.py:114

Functionf_load

()

models/autoencoder.py:247

Functionf_load

()

models/transition.py:113

Functionf_save

(step)

models/conditional.py:121

Functionf_save

(step)

models/autoencoder.py:256

Functionf_save

(step)

models/transition.py:120

(image_path, image_size, is_crop=True)

models/utils.py:17

Functionget_model

(sess, image_shape=(80, 160, 3), gf_dim=64, df_dim=64, batch_size=64, name="transition", gpu=0)

models/conditional.py:46

Functionget_model

(sess, image_shape=(80, 160, 3), gf_dim=64, df_dim=64, batch_size=64, name="autoencoder", gpu=0)

models/autoencoder.py:130

Methodget_output_shape_for

(self, input_shape)

models/layers.py:393

Methodget_output_shape_for

(shape, mean=1., scale=0.02, name=None)

models/conditional.py:24

Functionmean_normal

(shape, mean=1., scale=0.02, name=None)

models/autoencoder.py:31

Functionmean_normal

(shape, mean=1., scale=0.02, name=None)

models/transition.py:24

train_generative_model.py:22

Functionsampler

(z, x)

models/conditional.py:125

Functionsampler

(z, x)

models/autoencoder.py:262

(output_path, *layers)

models/utils.py:69

Functiontrain_d

(images, z, counter, sess=sess)

models/conditional.py:102

Functiontrain_d

(images, z, counter, sess=sess)

models/autoencoder.py:218

Functiontrain_d

(images, z, counter, sess=sess)

models/transition.py:101

Functiontrain_g

(images, z, counter, sess=sess)

models/conditional.py:105

Functiontrain_g

(images, z, counter, sess=sess)

models/autoencoder.py:228

Functiontrain_g

(images, z, counter, sess=sess)

models/transition.py:104

Functionvisualize

(sess, dcgan, config, option)

models/utils.py:149