问Tensorflow的TripletSemiHardLoss和TripletHardLoss是如何使用的，以及如何在暹罗网络中使用？

EN

# Build pairwise binary adjacency matrix.
adjacency = tf.math.equal(labels, tf.transpose(labels))
# Invert so we can select negatives only.
adjacency_not = tf.math.logical_not(adjacency)

adjacency_not = tf.cast(adjacency_not, dtype=tf.dtypes.float32)
# hard negatives: smallest D_an.
hard_negatives = _masked_minimum(pdist_matrix, adjacency_not)

batch_size = tf.size(labels)

adjacency = tf.cast(adjacency, dtype=tf.dtypes.float32)

mask_positives = tf.cast(adjacency, dtype=tf.dtypes.float32) - tf.linalg.diag(
    tf.ones([batch_size])
)

# hard positives: largest D_ap.
hard_positives = _masked_maximum(pdist_matrix, mask_positives)

if soft:
    triplet_loss = tf.math.log1p(tf.math.exp(hard_positives - hard_negatives))
else:
    triplet_loss = tf.maximum(hard_positives - hard_negatives + margin, 0.0)

# Get final mean triplet loss
triplet_loss = tf.reduce_mean(triplet_loss)

# Build pairwise binary adjacency matrix.
adjacency = tf.math.equal(labels, tf.transpose(labels))
# Invert so we can select negatives only.
adjacency_not = tf.math.logical_not(adjacency)

batch_size = tf.size(labels)

# Compute the mask.
pdist_matrix_tile = tf.tile(pdist_matrix, [batch_size, 1])
mask = tf.math.logical_and(
    tf.tile(adjacency_not, [batch_size, 1]),
    tf.math.greater(
        pdist_matrix_tile, tf.reshape(tf.transpose(pdist_matrix), [-1, 1])
    ),
)
mask_final = tf.reshape(
    tf.math.greater(
        tf.math.reduce_sum(
            tf.cast(mask, dtype=tf.dtypes.float32), 1, keepdims=True
        ),
        0.0,
    ),
    [batch_size, batch_size],
)
mask_final = tf.transpose(mask_final)

adjacency_not = tf.cast(adjacency_not, dtype=tf.dtypes.float32)
mask = tf.cast(mask, dtype=tf.dtypes.float32)

# negatives_outside: smallest D_an where D_an > D_ap.
negatives_outside = tf.reshape(
    _masked_minimum(pdist_matrix_tile, mask), [batch_size, batch_size]
)
negatives_outside = tf.transpose(negatives_outside)

# negatives_inside: largest D_an.
negatives_inside = tf.tile(
    _masked_maximum(pdist_matrix, adjacency_not), [1, batch_size]
)
semi_hard_negatives = tf.where(mask_final, negatives_outside, negatives_inside)

loss_mat = tf.math.add(margin, pdist_matrix - semi_hard_negatives)

mask_positives = tf.cast(adjacency, dtype=tf.dtypes.float32) - tf.linalg.diag(
    tf.ones([batch_size])
)

# In lifted-struct, the authors multiply 0.5 for upper triangular
#   in semihard, they take all positive pairs except the diagonal.
num_positives = tf.math.reduce_sum(mask_positives)

triplet_loss = tf.math.truediv(
    tf.math.reduce_sum(
        tf.math.maximum(tf.math.multiply(loss_mat, mask_positives), 0.0)
    ),
    num_positives,
)

import tensorflow as tf
import tensorflow_addons as tfa
import tensorflow_datasets as tfds

def _normalize_img(img, label):
    img = tf.cast(img, tf.float32) / 255.
    return (img, label)

train_dataset, test_dataset = tfds.load(name="mnist", split=['train', 'test'], as_supervised=True)

# Build your input pipelines
train_dataset = train_dataset.shuffle(1024).batch(16)
train_dataset = train_dataset.map(_normalize_img)

# Take one batch of data
for data in train_dataset.take(1):
    print("Batch of images shape:\n{}\nBatch of labels:\n{}\n".format(data[0].shape, data[1]))

Batch of images shape:
(16, 28, 28, 1)
Batch of labels:
[8 4 0 3 2 4 5 1 0 5 7 0 2 6 4 9]