tensorflow/tensorflow/python/keras/layers/merge.py at master · codeplaysoftware/tensorflow · GitHub

Repository navigation

History

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

# Licensed under the Apache License, Version 2.0 (the "License");

# you may not use this file except in compliance with the License.

# You may obtain a copy of the License at

# http://www.apache.org/licenses/LICENSE-2.0

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

# ==============================================================================

# pylint: disable=not-callable

# pylint: disable=redefined-builtin

"""Layers that can merge several inputs into one.

"""

from __future__ import absolute_import

from __future__ import division

from __future__ import print_function

from tensorflow.python.keras import backend as K

from tensorflow.python.keras.engine.base_layer import Layer

from tensorflow.python.keras.utils import tf_utils

from tensorflow.python.ops import array_ops

from tensorflow.python.ops import math_ops

from tensorflow.python.ops import nn

from tensorflow.python.util.tf_export import tf_export

class _Merge(Layer):

"""Generic merge layer for elementwise merge functions.

Used to implement `Sum`, `Average`, etc.

Arguments:

**kwargs: standard layer keyword arguments.

"""

def __init__(self, **kwargs):

super(_Merge, self).__init__(**kwargs)

self.supports_masking = True

def _merge_function(self, inputs):

raise NotImplementedError

def _compute_elemwise_op_output_shape(self, shape1, shape2):

"""Computes the shape of the resultant of an elementwise operation.

Arguments:

shape1: tuple or None. Shape of the first tensor

shape2: tuple or None. Shape of the second tensor

Returns:

expected output shape when an element-wise operation is

carried out on 2 tensors with shapes shape1 and shape2.

tuple or None.

Raises:

ValueError: if shape1 and shape2 are not compatible for

element-wise operations.

"""

if None in [shape1, shape2]:

return None

elif len(shape1) < len(shape2):

return self._compute_elemwise_op_output_shape(shape2, shape1)

elif not shape2:

return shape1

output_shape = list(shape1[:-len(shape2)])

for i, j in zip(shape1[-len(shape2):], shape2):

if i is None or j is None:

output_shape.append(None)

elif i == 1:

output_shape.append(j)

elif j == 1:

output_shape.append(i)

else:

if i != j:

raise ValueError(

'Operands could not be broadcast '

'together with shapes ' + str(shape1) + ' ' + str(shape2))

output_shape.append(i)

return tuple(output_shape)

@tf_utils.shape_type_conversion

def build(self, input_shape):

# Used purely for shape validation.

if not isinstance(input_shape, list):

raise ValueError('A merge layer should be called ' 'on a list of inputs.')

if len(input_shape) < 2:

raise ValueError('A merge layer should be called '

'on a list of at least 2 inputs. '

'Got ' + str(len(input_shape)) + ' inputs.')

batch_sizes = [s[0] for s in input_shape if s is not None]

batch_sizes = set(batch_sizes)

batch_sizes -= set([None])

if len(batch_sizes) > 1:

raise ValueError(

'Can not merge tensors with different '

'batch sizes. Got tensors with shapes : ' + str(input_shape))

if input_shape[0] is None:

output_shape = None

else:

output_shape = input_shape[0][1:]

for i in range(1, len(input_shape)):

if input_shape[i] is None:

shape = None

else:

shape = input_shape[i][1:]

output_shape = self._compute_elemwise_op_output_shape(output_shape, shape)

# If the inputs have different ranks, we have to reshape them

# to make them broadcastable.

if None not in input_shape and len(set(map(len, input_shape))) == 1:

self._reshape_required = False

else:

self._reshape_required = True

def call(self, inputs):

if not isinstance(inputs, list):

raise ValueError('A merge layer should be called ' 'on a list of inputs.')

if self._reshape_required:

reshaped_inputs = []

input_ndims = list(map(K.ndim, inputs))

if None not in input_ndims:

# If ranks of all inputs are available,

# we simply expand each of them at axis=1

# until all of them have the same rank.

max_ndim = max(input_ndims)

for x in inputs:

x_ndim = K.ndim(x)

for _ in range(max_ndim - x_ndim):

x = array_ops.expand_dims(x, axis=1)

reshaped_inputs.append(x)

return self._merge_function(reshaped_inputs)

else:

# Transpose all inputs so that batch size is the last dimension.

# (batch_size, dim1, dim2, ... ) -> (dim1, dim2, ... , batch_size)

transposed = False

for x in inputs:

x_ndim = K.ndim(x)

if x_ndim is None:

x_shape = array_ops.shape(x)

batch_size = x_shape[0]

new_shape = K.concatenate(

[x_shape[1:],

array_ops.expand_dims(batch_size, axis=-1)])

x_transposed = array_ops.reshape(

array_ops.stack(

[batch_size, math_ops.reduce_prod(x_shape[1:])], axis=0))

x_transposed = array_ops.transpose(x_transposed, perm=(1, 0))

x_transposed = array_ops.reshape(x_transposed, new_shape)

reshaped_inputs.append(x_transposed)

transposed = True

elif x_ndim > 1:

dims = list(range(1, x_ndim)) + [0]

reshaped_inputs.append(array_ops.transpose(x, perm=dims))

transposed = True

else:

# We don't transpose inputs if they are 1D vectors or scalars.

reshaped_inputs.append(x)

y = self._merge_function(reshaped_inputs)

y_ndim = K.ndim(y)

if transposed:

# If inputs have been transposed, we have to transpose the output too.

if y_ndim is None:

y_shape = array_ops.shape(y)

y_ndim = array_ops.shape(y_shape)[0]

batch_size = y_shape[y_ndim - 1]

new_shape = K.concatenate([

array_ops.expand_dims(batch_size, axis=-1), y_shape[:y_ndim - 1]

])

y = array_ops.reshape(y, (-1, batch_size))

y = array_ops.transpose(y, perm=(1, 0))

y = array_ops.reshape(y, new_shape)

elif y_ndim > 1:

dims = [y_ndim - 1] + list(range(y_ndim - 1))

y = array_ops.transpose(y, perm=dims)

return y

else:

return self._merge_function(inputs)

@tf_utils.shape_type_conversion

def compute_output_shape(self, input_shape):

if input_shape[0] is None:

output_shape = None

else:

output_shape = input_shape[0][1:]

for i in range(1, len(input_shape)):

if input_shape[i] is None:

shape = None

else:

shape = input_shape[i][1:]

output_shape = self._compute_elemwise_op_output_shape(output_shape, shape)

batch_sizes = [s[0] for s in input_shape if s is not None]

batch_sizes = set(batch_sizes)

batch_sizes -= set([None])

if len(batch_sizes) == 1:

output_shape = (list(batch_sizes)[0],) + output_shape

else:

output_shape = (None,) + output_shape

return output_shape

def compute_mask(self, inputs, mask=None):

if mask is None:

return None

if not isinstance(mask, list):

raise ValueError('`mask` should be a list.')

if not isinstance(inputs, list):

raise ValueError('`inputs` should be a list.')

if len(mask) != len(inputs):

raise ValueError('The lists `inputs` and `mask` '

'should have the same length.')

if all([m is None for m in mask]):

return None

masks = [array_ops.expand_dims(m, axis=0) for m in mask if m is not None]

return K.all(K.concatenate(masks, axis=0), axis=0, keepdims=False)

@tf_export('keras.layers.Add')

class Add(_Merge):

"""Layer that adds a list of inputs.

It takes as input a list of tensors,

all of the same shape, and returns

a single tensor (also of the same shape).

Examples:

```python

import keras

input1 = keras.layers.Input(shape=(16,))

x1 = keras.layers.Dense(8, activation='relu')(input1)

input2 = keras.layers.Input(shape=(32,))

x2 = keras.layers.Dense(8, activation='relu')(input2)

added = keras.layers.Add()([x1, x2]) # equivalent to added =

keras.layers.add([x1, x2])

out = keras.layers.Dense(4)(added)

model = keras.models.Model(inputs=[input1, input2], outputs=out)

```

"""

def _merge_function(self, inputs):

output = inputs[0]

for i in range(1, len(inputs)):

output += inputs[i]

return output

class Subtract(_Merge):

"""Layer that subtracts two inputs.

It takes as input a list of tensors of size 2,

both of the same shape, and returns a single tensor, (inputs[0] - inputs[1]),

also of the same shape.

Examples:

```python

import keras

input1 = keras.layers.Input(shape=(16,))

x1 = keras.layers.Dense(8, activation='relu')(input1)

input2 = keras.layers.Input(shape=(32,))

x2 = keras.layers.Dense(8, activation='relu')(input2)

# Equivalent to subtracted = keras.layers.subtract([x1, x2])

subtracted = keras.layers.Subtract()([x1, x2])

out = keras.layers.Dense(4)(subtracted)

model = keras.models.Model(inputs=[input1, input2], outputs=out)

```

"""

@tf_utils.shape_type_conversion

def build(self, input_shape):

super(Subtract, self).build(input_shape)

if len(input_shape) != 2:

raise ValueError('A `Subtract` layer should be called '

'on exactly 2 inputs')

def _merge_function(self, inputs):

if len(inputs) != 2:

raise ValueError('A `Subtract` layer should be called '

'on exactly 2 inputs')

return inputs[0] - inputs[1]

@tf_export('keras.layers.Multiply')

class Multiply(_Merge):

"""Layer that multiplies (element-wise) a list of inputs.

It takes as input a list of tensors,

all of the same shape, and returns

a single tensor (also of the same shape).

"""

def _merge_function(self, inputs):

output = inputs[0]

for i in range(1, len(inputs)):

output *= inputs[i]

return output

@tf_export('keras.layers.Average')

class Average(_Merge):

"""Layer that averages a list of inputs.

It takes as input a list of tensors,

all of the same shape, and returns

a single tensor (also of the same shape).

"""

def _merge_function(self, inputs):

output = inputs[0]

for i in range(1, len(inputs)):

output += inputs[i]

return output / len(inputs)

@tf_export('keras.layers.Maximum')

class Maximum(_Merge):

"""Layer that computes the maximum (element-wise) a list of inputs.

It takes as input a list of tensors,

all of the same shape, and returns

a single tensor (also of the same shape).

"""

def _merge_function(self, inputs):

output = inputs[0]

for i in range(1, len(inputs)):

output = math_ops.maximum(output, inputs[i])

return output

class Minimum(_Merge):

"""Layer that computes the minimum (element-wise) a list of inputs.

It takes as input a list of tensors,

all of the same shape, and returns

a single tensor (also of the same shape).

"""

def _merge_function(self, inputs):

output = inputs[0]

for i in range(1, len(inputs)):

output = math_ops.minimum(output, inputs[i])

return output

@tf_export('keras.layers.Concatenate')

class Concatenate(_Merge):

"""Layer that concatenates a list of inputs.

It takes as input a list of tensors,

all of the same shape except for the concatenation axis,

and returns a single tensor, the concatenation of all inputs.

Arguments:

axis: Axis along which to concatenate.

**kwargs: standard layer keyword arguments.

"""

def __init__(self, axis=-1, **kwargs):

super(Concatenate, self).__init__(**kwargs)

self.axis = axis

self.supports_masking = True

self._reshape_required = False

@tf_utils.shape_type_conversion

def build(self, input_shape):

# Used purely for shape validation.

if not isinstance(input_shape, list) or len(input_shape) < 2:

raise ValueError('A `Concatenate` layer should be called '

'on a list of at least 2 inputs')

if all([shape is None for shape in input_shape]):

return

reduced_inputs_shapes = [list(shape) for shape in input_shape]

shape_set = set()

for i in range(len(reduced_inputs_shapes)):

del reduced_inputs_shapes[i][self.axis]

shape_set.add(tuple(reduced_inputs_shapes[i]))

if len(shape_set) > 1:

raise ValueError('A `Concatenate` layer requires '

'inputs with matching shapes '

'except for the concat axis. '

'Got inputs shapes: %s' % (input_shape))

def _merge_function(self, inputs):

return K.concatenate(inputs, axis=self.axis)

@tf_utils.shape_type_conversion

def compute_output_shape(self, input_shape):

if not isinstance(input_shape, list):

raise ValueError('A `Concatenate` layer should be called '

'on a list of inputs.')

input_shapes = input_shape

output_shape = list(input_shapes[0])

for shape in input_shapes[1:]:

if output_shape[self.axis] is None or shape[self.axis] is None:

output_shape[self.axis] = None

break

output_shape[self.axis] += shape[self.axis]

return tuple(output_shape)

def compute_mask(self, inputs, mask=None):

if mask is None:

return None

if not isinstance(mask, list):

raise ValueError('`mask` should be a list.')

if not isinstance(inputs, list):

raise ValueError('`inputs` should be a list.')

if len(mask) != len(inputs):

raise ValueError('The lists `inputs` and `mask` '

'should have the same length.')

if all([m is None for m in mask]):

return None

# Make a list of masks while making sure

# the dimensionality of each mask

# is the same as the corresponding input.

masks = []

for input_i, mask_i in zip(inputs, mask):

if mask_i is None:

# Input is unmasked. Append all 1s to masks,

masks.append(array_ops.ones_like(input_i, dtype='bool'))

elif K.ndim(mask_i) < K.ndim(input_i):

# Mask is smaller than the input, expand it

masks.append(array_ops.expand_dims(mask_i, axis=-1))

else:

masks.append(mask_i)

concatenated = K.concatenate(masks, axis=self.axis)

return K.all(concatenated, axis=-1, keepdims=False)

def get_config(self):

config = {

'axis': self.axis,

}

base_config = super(Concatenate, self).get_config()

return dict(list(base_config.items()) + list(config.items()))

@tf_export('keras.layers.Dot')

class Dot(_Merge):

"""Layer that computes a dot product between samples in two tensors.

E.g. if applied to two tensors `a` and `b` of shape `(batch_size, n)`,

the output will be a tensor of shape `(batch_size, 1)`

where each entry `i` will be the dot product between

`a[i]` and `b[i]`.

Arguments:

axes: Integer or tuple of integers,

axis or axes along which to take the dot product.

normalize: Whether to L2-normalize samples along the

dot product axis before taking the dot product.

If set to True, then the output of the dot product

is the cosine proximity between the two samples.

**kwargs: Standard layer keyword arguments.

"""

def __init__(self, axes, normalize=False, **kwargs):

super(Dot, self).__init__(**kwargs)

if not isinstance(axes, int):

if not isinstance(axes, (list, tuple)):

raise TypeError('Invalid type for `axes` - '

'should be a list or an int.')

if len(axes) != 2:

raise ValueError('Invalid format for `axes` - '

'should contain two elements.')

if not isinstance(axes[0], int) or not isinstance(axes[1], int):

raise ValueError('Invalid format for `axes` - '

'list elements should be "int".')

self.axes = axes

self.normalize = normalize

self.supports_masking = True

self._reshape_required = False

@tf_utils.shape_type_conversion

def build(self, input_shape):

# Used purely for shape validation.

if not isinstance(input_shape, list) or len(input_shape) != 2:

raise ValueError('A `Dot` layer should be called '

'on a list of 2 inputs.')

shape1 = input_shape[0]

shape2 = input_shape[1]

if shape1 is None or shape2 is None:

return

if isinstance(self.axes, int):

if self.axes < 0:

axes = [self.axes % len(shape1), self.axes % len(shape2)]

else:

axes = [self.axes] * 2

else:

axes = self.axes

if shape1[axes[0]] != shape2[axes[1]]:

raise ValueError('Dimension incompatibility '

'%s != %s. ' % (shape1[axes[0]], shape2[axes[1]]) +

'Layer shapes: %s, %s' % (shape1, shape2))

def _merge_function(self, inputs):

if len(inputs) != 2:

raise ValueError('A `Dot` layer should be called ' 'on exactly 2 inputs')

x1 = inputs[0]

x2 = inputs[1]

if isinstance(self.axes, int):

if self.axes < 0:

axes = [self.axes % K.ndim(x1), self.axes % K.ndim(x2)]

else:

axes = [self.axes] * 2

else:

axes = []

for i in range(len(self.axes)):

if self.axes[i] < 0:

axes.append(self.axes[i] % K.ndim(inputs[i]))

else:

axes.append(self.axes[i])

if self.normalize:

x1 = nn.l2_normalize(x1, axis=axes[0])

x2 = nn.l2_normalize(x2, axis=axes[1])

output = K.batch_dot(x1, x2, axes)

return output

@tf_utils.shape_type_conversion

def compute_output_shape(self, input_shape):

if not isinstance(input_shape, list) or len(input_shape) != 2:

raise ValueError('A `Dot` layer should be called '

'on a list of 2 inputs.')

shape1 = list(input_shape[0])

shape2 = list(input_shape[1])

if isinstance(self.axes, int):

if self.axes < 0:

axes = [self.axes % len(shape1), self.axes % len(shape2)]

else:

axes = [self.axes] * 2

else:

axes = self.axes

shape1.pop(axes[0])

shape2.pop(axes[1])

shape2.pop(0)

output_shape = shape1 + shape2

if len(output_shape) == 1:

output_shape += [1]

return tuple(output_shape)

def compute_mask(self, inputs, mask=None):

return None

def get_config(self):

config = {

'axes': self.axes,

'normalize': self.normalize,

}

base_config = super(Dot, self).get_config()

return dict(list(base_config.items()) + list(config.items()))

@tf_export('keras.layers.add')

def add(inputs, **kwargs):

"""Functional interface to the `Add` layer.

Arguments:

inputs: A list of input tensors (at least 2).

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the sum of the inputs.

Examples:

```python

import keras

input1 = keras.layers.Input(shape=(16,))

x1 = keras.layers.Dense(8, activation='relu')(input1)

input2 = keras.layers.Input(shape=(32,))

x2 = keras.layers.Dense(8, activation='relu')(input2)

added = keras.layers.add([x1, x2])

out = keras.layers.Dense(4)(added)

model = keras.models.Model(inputs=[input1, input2], outputs=out)

```

"""

return Add(**kwargs)(inputs)

def subtract(inputs, **kwargs):

"""Functional interface to the `Subtract` layer.

Arguments:

inputs: A list of input tensors (exactly 2).

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the difference of the inputs.

Examples:

```python

import keras

input1 = keras.layers.Input(shape=(16,))

x1 = keras.layers.Dense(8, activation='relu')(input1)

input2 = keras.layers.Input(shape=(32,))

x2 = keras.layers.Dense(8, activation='relu')(input2)

subtracted = keras.layers.subtract([x1, x2])

out = keras.layers.Dense(4)(subtracted)

model = keras.models.Model(inputs=[input1, input2], outputs=out)

```

"""

return Subtract(**kwargs)(inputs)

@tf_export('keras.layers.multiply')

def multiply(inputs, **kwargs):

"""Functional interface to the `Multiply` layer.

Arguments:

inputs: A list of input tensors (at least 2).

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the element-wise product of the inputs.

"""

return Multiply(**kwargs)(inputs)

@tf_export('keras.layers.average')

def average(inputs, **kwargs):

"""Functional interface to the `Average` layer.

Arguments:

inputs: A list of input tensors (at least 2).

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the average of the inputs.

"""

return Average(**kwargs)(inputs)

@tf_export('keras.layers.maximum')

def maximum(inputs, **kwargs):

"""Functional interface to the `Maximum` layer.

Arguments:

inputs: A list of input tensors (at least 2).

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the element-wise maximum of the inputs.

"""

return Maximum(**kwargs)(inputs)

def minimum(inputs, **kwargs):

"""Functional interface to the `Minimum` layer.

Arguments:

inputs: A list of input tensors (at least 2).

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the element-wise minimum of the inputs.

"""

return Minimum(**kwargs)(inputs)

@tf_export('keras.layers.concatenate')

def concatenate(inputs, axis=-1, **kwargs):

"""Functional interface to the `Concatenate` layer.

Arguments:

inputs: A list of input tensors (at least 2).

axis: Concatenation axis.

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the concatenation of the inputs alongside axis `axis`.

"""

return Concatenate(axis=axis, **kwargs)(inputs)

@tf_export('keras.layers.dot')

def dot(inputs, axes, normalize=False, **kwargs):

"""Functional interface to the `Dot` layer.

Arguments:

inputs: A list of input tensors (at least 2).

axes: Integer or tuple of integers,

axis or axes along which to take the dot product.

normalize: Whether to L2-normalize samples along the

dot product axis before taking the dot product.

If set to True, then the output of the dot product

is the cosine proximity between the two samples.

**kwargs: Standard layer keyword arguments.

Returns:

A tensor, the dot product of the samples from the inputs.

"""

return Dot(axes=axes, normalize=normalize, **kwargs)(inputs)

tensorflow/tensorflow/python/keras/layers/merge.py at master · codeplaysoftware/tensorflow · GitHub

Repository navigation

Expand file tree

Breadcrumbs

merge.py

Latest commit

History

Breadcrumbs

merge.py

File metadata and controls