Functions — github.com/davidsandberg/facenet

hub / github.com/davidsandberg/facenet / functions

Functions312 in github.com/davidsandberg/facenet

⨍ Functions 312◇ Types & classes 20

↓ 24 callersMethodconv

(self, inp, k_h, k_w, c_o, s_h,

src/align/detect_face.py:132

↓ 16 callersMethodmax_pool

(self, inp, k_h, k_w, s_h, s_w, name, padding='SAME')

src/align/detect_face.py:175

↓ 16 callersFunctionvbbConstants

(layerNumber)

tmp/vggface16.py:20

↓ 16 callersFunctionvbbConstants

(layerNumber)

tmp/vggverydeep19.py:19

↓ 16 callersFunctionvbbWeights

(layerNumber)

tmp/vggface16.py:15

↓ 16 callersFunctionvbbWeights

(layerNumber)

tmp/vggverydeep19.py:14

↓ 15 callersMethodload

Load network weights. data_path: The path to the numpy-serialized network weights session: The current TensorFlow session igno

src/align/detect_face.py:79

↓ 13 callersFunctiondata_type

Return the type of the activations, weights, and placeholder variables.

tmp/mnist_center_loss.py:58

↓ 12 callersMethodprelu

(self, inp, name)

src/align/detect_face.py:167

↓ 11 callersFunctiondata_type

Return the type of the activations, weights, and placeholder variables.

tmp/mnist_noise_labels.py:57

↓ 9 callersFunctionT

Helper for getting layer output tensor

tmp/deepdream.py:85

↓ 8 callersMethodfeed

Set the input(s) for the next operation by replacing the terminal nodes. The arguments can be either layer names or the actual layers.

src/align/detect_face.py:97

↓ 8 callersFunctionfire_module

(inputs, squeeze_depth, expand_depth, reuse=None,

src/models/squeezenet.py:8

↓ 8 callersFunctionnms

(boxes, threshold, method)

src/align/detect_face.py:687

↓ 8 callersMethodsoftmax

(self, target, axis, name=None)

src/align/detect_face.py:209

↓ 7 callersMethodfc

(self, inp, num_out, name, relu=True)

src/align/detect_face.py:184

↓ 6 callersFunctionconv

(inpOp, nIn, nOut, kH, kW, dH, dW, padType, name, phase_train=True, use_batch_norm=True, weight_decay=0.0)

tmp/network.py:35

↓ 6 callersFunctionimresample

(img, sz)

src/align/detect_face.py:765

↓ 5 callersFunction_affine

(inpOp, nIn, nOut)

tmp/seed_test.py:102

↓ 5 callersFunctionget_control_flag

(control, field)

src/facenet.py:139

↓ 5 callersMethodmake_var

Creates a new TensorFlow variable.

src/align/detect_face.py:123

↓ 5 callersFunctionresize

(img, size)

tmp/deepdream.py:114

↓ 5 callersFunctionshowarray

(a)

tmp/deepdream.py:76

↓ 4 callersFunctionadd_extension

(path)

src/lfw.py:69

↓ 4 callersFunctionbbreg

Calibrate bounding boxes

src/align/detect_face.py:646

↓ 4 callersFunctionevaluate_accuracy

(sess, images_placeholder, phase_train_placeholder, image_size, embeddings, paths, actual_issame, aug

tmp/test_invariance_on_lfw.py:139

↓ 4 callersFunctionmaybe_download

Download the data from Yann's website, unless it's already here.

tmp/mnist_center_loss.py:66

↓ 4 callersFunctionmaybe_download

Download the data from Yann's website, unless it's already here.

tmp/mnist_noise_labels.py:65

↓ 4 callersFunctionpad

Compute the padding coordinates (pad the bounding boxes to square)

src/align/detect_face.py:720

↓ 4 callersFunctionrender_lapnorm

(t_obj, img0=img_noise, visfunc=visstd, iter_n=10, step=1.0, octave_n=3, octave_scale=1

tmp/deepdream.py:191

↓ 4 callersFunctionrerec

Convert bboxA to square.

src/align/detect_face.py:755

↓ 4 callersFunctionsave_result

(aug, acc, filename)

tmp/test_invariance_on_lfw.py:134

↓ 3 callersFunctioncalc_grad_tiled

Compute the value of tensor t_grad over the image in a tiled way. Random shifts are applied to the image to blur tile boundaries over

tmp/deepdream.py:120

↓ 3 callersFunctioncalculate_accuracy

(threshold, dist, actual_issame)

src/facenet.py:457

↓ 3 callersMethodencoder

(self, images, is_training)

src/generative/models/dfc_vae.py:42

↓ 3 callersFunctionerror_rate

Return the error rate based on dense predictions and sparse labels.

tmp/mnist_center_loss.py:116

↓ 3 callersFunctionerror_rate

Return the error rate based on dense predictions and sparse labels.

tmp/mnist_noise_labels.py:115

↓ 3 callersFunctionfake_data

Generate a fake dataset that matches the dimensions of MNIST.

tmp/mnist_center_loss.py:103

↓ 3 callersFunctionfake_data

Generate a fake dataset that matches the dimensions of MNIST.

tmp/mnist_noise_labels.py:102

↓ 3 callersFunctionget_batch

(image_data, batch_size, batch_index)

src/facenet.py:269

↓ 3 callersMethodget_image_size

(self)

src/generative/models/vae_base.py:56

↓ 2 callersFunctionT

Helper for getting layer output tensor

tmp/visualize.py:86

↓ 2 callersFunctioncalculate_val_far

(threshold, dist, actual_issame)

src/facenet.py:508

↓ 2 callersMethoddecoder

(self, latent_var, is_training)

src/generative/models/dfc_vae.py:62

↓ 2 callersFunctiondistance

(embeddings1, embeddings2, distance_metric=0)

src/facenet.py:408

↓ 2 callersFunctioneval_in_batches

Get all predictions for a dataset by running it in small batches.

tmp/mnist_center_loss.py:316

↓ 2 callersFunctioneval_in_batches

Get all predictions for a dataset by running it in small batches.

tmp/mnist_noise_labels.py:286

↓ 2 callersFunctionextract_data

Extract the images into a 4D tensor [image index, y, x, channels]. Values are rescaled from [0, 255] down to [-0.5, 0.5].

tmp/mnist_center_loss.py:79

↓ 2 callersFunctionextract_data

Extract the images into a 4D tensor [image index, y, x, channels]. Values are rescaled from [0, 255] down to [-0.5, 0.5].

tmp/mnist_noise_labels.py:78

↓ 2 callersFunctionextract_labels

Extract the labels into a vector of int64 label IDs.

tmp/mnist_center_loss.py:93

↓ 2 callersFunctionextract_labels

Extract the labels into a vector of int64 label IDs.

tmp/mnist_noise_labels.py:92

↓ 2 callersMethodfind_faces

(self, image)

contributed/face.py:135

↓ 2 callersFunctiongenerateBoundingBox

Use heatmap to generate bounding boxes

src/align/detect_face.py:660

↓ 2 callersMethodgenerate_embedding

(self, face)

contributed/face.py:104

↓ 2 callersFunctionl2_loss

Define a L2Loss, useful for regularize, i.e. weight decay. Args: tensor: tensor to regularize. weight: an optional weight to modulate

tmp/network.py:62

↓ 2 callersFunctionmemory_usage_psutil

()

test/train_test.py:32

↓ 2 callersFunctionmodel

The Model definition.

tmp/mnist_center_loss.py:231

↓ 2 callersFunctionmodel

The Model definition.

tmp/mnist_noise_labels.py:195

↓ 2 callersFunctionrender_deepdream

(t_obj, img0=img_noise, iter_n=10, step=1.5, octave_n=4, octave_scale=1.4)

tmp/deepdream.py:209

↓ 2 callersFunctionrun_train

()

tmp/seed_test.py:25

↓ 2 callersFunctionsave_error_message_file

(filename, error_message)

tmp/download_vgg_face_dataset.py:83

↓ 2 callersFunctiontffunc

Helper that transforms TF-graph generating function into a regular one. See "resize" function below.

tmp/deepdream.py:101

↓ 2 callersMethodvalidate_padding

Verifies that the padding is one of the supported ones.

src/align/detect_face.py:127

↓ 2 callersFunctionvisstd

Normalize the image range for visualization

tmp/deepdream.py:81

↓ 1 callersFunctionTemporaryDirectory

()

tmp/funnel_dataset.py:19

↓ 1 callersFunction_add_loss_summaries

Add summaries for losses. Generates moving average for all losses and associated summaries for visualizing the performance of the network.

src/facenet.py:142

↓ 1 callersFunction_chinese_whispers

Chinese Whispers Algorithm Modified from Alex Loveless' implementation, http://alexloveless.co.uk/data/chinese-whispers-graph-clustering-in-

contributed/clustering.py:29

↓ 1 callersFunction_conv

(inpOp, nIn, nOut, kH, kW, dH, dW, padType)

tmp/seed_test.py:90

↓ 1 callersMethod_setup_mtcnn

(self)

contributed/face.py:128

↓ 1 callersFunctionadd_overlays

(frame, faces, frame_rate)

contributed/real_time_face_recognition.py:36

↓ 1 callersMethodalign

r"""align(imgDim, rgbImg, bb=None, landmarks=None, landmarkIndices=INNER_EYES_AND_BOTTOM_LIP) Transform and align a face in an image.

tmp/align_dlib.py:158

↓ 1 callersFunctionalign_data

(image_list, image_size, margin, pnet, rnet, onet)

contributed/cluster.py:117

↓ 1 callersFunctionalign_dataset_if_needed

(self)

test/train_test.py:39

↓ 1 callersFunctionbatch_norm

Batch normalization on convolutional maps. Args: x: Tensor, 4D BHWD input maps n_out: integer, depth of input

tmp/network.py:114

↓ 1 callersFunctionblock8

Builds the 8x8 resnet block.

src/models/inception_resnet_v1.py:72

↓ 1 callersFunctionblock8

Builds the 8x8 resnet block.

src/models/inception_resnet_v2.py:72

↓ 1 callersFunctioncalculate_embeddings

Get all predictions for a dataset by running it in small batches.

tmp/mnist_center_loss.py:335

↓ 1 callersFunctioncluster_facial_encodings

Cluster facial encodings Intended to be an optional switch for different clustering algorithms, as of right now only chinese whisper

contributed/clustering.py:130

↓ 1 callersFunctioncompute_facial_encodings

Compute Facial Encodings Given a set of images, compute the facial encodings of each face detected in the images and return them. If

contributed/clustering.py:153

↓ 1 callersFunctioncreate_features

(label_to_center, batch_size, nrof_features, labels)

test/center_loss_test.py:70

↓ 1 callersFunctioncreate_mock_dataset

(dataset_dir, image_size)

test/train_test.py:209

↓ 1 callersFunctioncreate_mock_lfw_pairs

(tmp_dir)

test/train_test.py:226

↓ 1 callersFunctioncreate_network_face_detection

(gpu_memory_fraction)

contributed/cluster.py:149

↓ 1 callersFunctioncrop

(image, random_crop, image_size)

src/facenet.py:220

↓ 1 callersFunctiondownload_file_from_google_drive

(file_id, destination)

src/download_and_extract.py:23

↓ 1 callersFunctionevaluate

(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholde

src/validate_on_lfw.py:86

↓ 1 callersFunctionevaluate

(sess, enqueue_op, image_paths_placeholder, labels_placeholder, phase_train_placeholder, batch_size_placeholde

src/train_softmax.py:397

↓ 1 callersFunctionevaluate

(sess, image_paths, embeddings, labels_batch, image_paths_placeholder, labels_placeholder, batch_size

src/train_tripletloss.py:341

↓ 1 callersFunctionexpand

(inputs, num_outputs)

src/models/squeezenet.py:24

↓ 1 callersFunctionface_distance

Given a list of face encodings, compare them to a known face encoding and get a euclidean distance for each comparison face. The distance tel

contributed/clustering.py:9

↓ 1 callersFunctionfilter_dataset

(dataset, data_filename, percentile, min_nrof_images_per_class)

src/train_softmax.py:273

↓ 1 callersMethodfindLandmarks

Find the landmarks of a face. :param rgbImg: RGB image to process. Shape: (height, width, 3) :type rgbImg: numpy.ndarray

tmp/align_dlib.py:139

↓ 1 callersFunctionfind_threshold

(var, percentile)

src/train_softmax.py:265

↓ 1 callersFunctionflip

(image, random_flip)

src/facenet.py:232

↓ 1 callersFunctionfreeze_graph_def

(sess, input_graph_def, output_node_names)

src/freeze_graph.py:65

↓ 1 callersMethodgetAllFaceBoundingBoxes

Find all face bounding boxes in an image. :param rgbImg: RGB image to process. Shape: (height, width, 3) :type rgbImg: numpy

tmp/align_dlib.py:102

↓ 1 callersMethodgetLargestFaceBoundingBox

Find the largest face bounding box in an image. :param rgbImg: RGB image to process. Shape: (height, width, 3) :type rgbImg:

tmp/align_dlib.py:120

↓ 1 callersFunctionget_confirm_token

(response)

src/download_and_extract.py:38

↓ 1 callersFunctionget_facenet_variables_to_restore

()

src/generative/train_vae.py:226

↓ 1 callersFunctionget_image_paths

(facedir)

src/facenet.py:332

next →1–100 of 312, ranked by callers