1 x 1 convolutions 176 – 179
adam optimizer 54, 58, 88, 113, 183, 229
Anaconda 615 – 616, 618 – 619
APIs (application programming interfaces) 599 – 612
predicting with TensorFlow serving API 608 – 612
TFX (TensorFlow-Extended) Trainer API 576 – 596
defining Keras model 577 – 584
defining model training 584 – 586
training Keras model with 589 – 596
validating infrastructure 600 – 601
ASICs (application-specific integrated circuits) 10
ASPP (atrous spatial pyramid pooling) module 273 – 275
defining final model 440 – 443
implementing Bahdanau attention in TensorFlow 436 – 440
attention_visualizer() function 446
auxiliary output layers 179 – 181
averaged_perceptron_tagger 303
Bahdanau attention in TensorFlow 436 – 440
BART (bidirectional and auto-regressive Transformers) 640 – 642
bert.bert_models.classifier_model() function 480
BERT (bidirectional encoder representations from Transformers) 350, 639
question answering with 505 – 508
spam classification using 463 – 483
bidirectional and auto-regressive Transformers (BART) 640 – 642
call() function 62, 64, 136, 333, 436
categorical_columns variable 596
categorical_crossentropy loss 54, 58, 335
CBOW (continuous bag-of-words) 457
central processing unit (CPU) 9 – 10
ce_weighted_from_logits() outer function 280
class imbalance 301, 471 – 474
CLI (command line interface) 619
CNNs (convolutional neural networks) 14, 90 – 105, 194 – 242, 522
Grad-CAM (gradient class activation map) 238 – 240
image classification with 149 – 193
creating data pipelines using Keras ImageData-Generator 160 – 165
exploratory data analysis 150 – 160
training model and evaluating performance 149 – 192
reducing overfitting 195 – 210
image data augmentation with Keras 196 – 203
using pretrained networks 232 – 238
computer graphic computations 19
Grad-CAM (gradient class activation map) 625 – 631
defining U-Net model 632 – 633
continuous bag-of-words (CBOW) 457
Conv2D layer 96 – 98, 101, 103 – 104, 150
cooking competition analogy 135 – 136
CPU (central processing unit) 9 – 10
CSVLogger callback 208 – 209, 586
DAG (directed acyclic graph) 25
declarative graph – based execution 27
DecoderRNNAttentionWrapper layer 440
implementing ASPP module 273 – 275
implementing Deeplab v3 using Keras functional API 270 – 273
deep learning 80 – 117, 119 – 146
CNNs (convolutional neural networks) 90 – 105
FCNs (fully connected networks) 81 – 90
generating text with 365 – 370
prototyping deep learning models 10
representing text as numbers 120 – 122
RNNs (recurrent neural networks) 105 – 117
Dense layer 53, 58, 87, 96, 103 – 104, 111 – 113, 145, 150, 179, 181, 218, 331, 334, 336, 369, 397, 522
dimensionality reduction method 176 – 179
directed acyclic graph (DAG) 25
DistilBERT 495 – 502, 640
DistilBertTokenizerFast.from_pretrained() function 488 – 489
EarlyStopping callback 207 – 209
EDA (exploratory data analysis) 150, 564 – 567
encoder-decoder pattern 123 – 124
English-German seq2seq machine translator 395 – 410
define TextVectorization layers for seq2seq model 400 – 401
defining decoder and final model 405 – 409
TextVectorization layer 398 – 400
activating and deactivating conda environment 622 – 623
running Jupyter Notebook server and creating notebooks 623
Unix-based environment 615 – 618
creating virtual Python environment with Anaconda distribution (Ubuntu) 615 – 616
prerequisites for GPU support (Ubuntu) 616 – 618
Windows Environments 618 – 622
creating Virtual Python Environment (Anaconda) 618 – 619
prerequisites for GPU support 619 – 622
image segmentation metrics 284 – 289
sequence-to-sequence learning 410 – 423
TFX (TensorFlow-Extended) model 602 – 608
exploratory data analysis 150 – 160, 564 – 567
factorization of embedding layer 643
FCNs (fully connected networks) 81 – 90
featurewise_center parameter 197
featurewise_std_normalization parameter 197
fix_random_seed function 56, 88
Flatten() layer 104, 181, 229, 522
flow_from_dataframe() function 73, 161, 164
flow_from_directory() function 161, 163 – 164
flow_from_directory() method 161 – 162
from_pretrained() function 495
fully connected layer 139 – 141, 456
gated recurrent units (GRUs) 10, 325, 350, 365 – 370, 396
get_bert_inputs() function 477
GLUE (General Language Understanding Evaluation) 468
GPT (generative pre-training) model 639 – 640
GPU (graphical processing unit) 9 – 10
Grad-CAM (gradient class activation map) 238 – 240, 625 – 631
GRUs (gated recurrent units) 10, 325, 350, 365 – 370, 396
hashing, locality sensitive 644 – 645
Hugging Face Transformers 483 – 509
defining DistilBERT model 495 – 502
defining and using tokenizer 488 – 493
from tokens to tf.data pipeline 493 – 494
i.i.d (independent and identically distributed) 105
ILSVRC (ImageNet Large Scale Visual Recognition Challenge) 151
image classification 149 – 193
creating data pipelines using Keras ImageData-Generator 160 – 165
exploratory data analysis 150 – 160
computing simple statistics on data set 158 – 160
Inception-ResNet v1 and Inception-ReSNet v2 187
Inception v1 169 – 181, 183 – 184
training model and evaluating performance 149 – 192
image data augmentation 196 – 203
implementing ASPP module 273 – 275
implementing Deeplab v3 using Keras functional API 270 – 273
TensorFlow data pipeline 251 – 265
final tf.data pipeline 264 – 265
optimizing tf.data pipelines 263 – 264
connection between sparsity and 175 – 176
Inception-ResNet v1 and Inception-ReSNet v2 187
Inception v1 169 – 181, 183 – 184
1 x 1 convolutions as dimensionality reduction method 176 – 179
auxiliary output layers 179 – 181
connection between Inception block and sparsity 175 – 176
Inception-ResNet type A block 216 – 223
Inception-ResNet type B block 223 – 225
Input layer 57 – 58, 582
input_shape parameter 53, 98, 117
input_shape (Sequential API) 70
image data augmentation with 196 – 203
functional API 56 – 61, 270 – 273
Keras ImageDataGenerator 160 – 165
language modeling 297, 349 – 384
GRUs (gated recurrent units) 365 – 370
measuring quality of generated text 370 – 372
defining tf.data pipeline 360 – 365
training and evaluating language model 372 – 374
LRN (local response normalization) 171 – 172, 213, 238
LSH (locality sensitive hashing) 644
LSTM (long short-term memory) 10, 326 – 331, 349
machine translation data 388 – 395
masked language modeling 351, 466
masked self-attention layers 136 – 138, 456
MaxPool2D layer 103 – 104, 150
Mean IoU (mean intersection over union) 287
mixed precision training 539 – 544
MLM (masked language modeling) 351, 466
MLP (multilayer perceptron) 20 – 21, 85
model.metric_names attribute 208
model.predict() function 293, 399
multi-head attention 138 – 139
NCE (Noise contrastive estimation) loss 355
NER (Named entity recognition) 297
neural network-related computations 39 – 45
neural networks with TFX Trainer API 576 – 596
defining Keras model 577 – 584
defining model training 584 – 586
training Keras model with TFX Trainer 589 – 596
next sentence prediction 466, 644
NLP (natural language processing) 120, 296 – 348, 639 – 645
defining end-to-end NLP pipeline with TensorFlow 319 – 325
GRUs (gated recurrent units) 365 – 370
measuring quality of generated text 370 – 372
training and evaluating 372 – 374
defining final model 331 – 336
analyzing sequence length 315 – 316
analyzing vocabulary 313 – 315
splitting training, validation and testing data 309 – 313
text to words and then to numbers with Keras 316 – 319
training and evaluating model 336 – 339
defining final model with word embeddings 341 – 344
training and evaluating model 344 – 346
nlp.optimization.create_optimizer() function 481
NLTK (Natural Language Toolkit) 302
Noise contrastive estimation (NCE) loss 355
np.random.normal() function 131
np.random.permutation() function 412
NSP (next-sentence prediction) 466, 644
Number of filters parameter 166
optimizing input pipeline 536 – 538
overfitting, reducing 195 – 210
image data augmentation with Keras 196 – 203
ParseFromString() function 569
Part of speech (PoS) tagging 297
PCA (Principal Component Analysis) 56, 548
pd.DataFrame.from_records() function 159
pd.Series.apply() function 156
pd.Series.str.len() function 315
performance bottlenecks 104, 529 – 544
mixed precision training 539 – 544
optimizing input pipeline 536 – 538
permutation language modeling 643
PoS (Part of speech) tagging 297
prepare_data(...) function 412
image segmentation with 266 – 277
implementing ASPP module 273 – 275
implementing Deeplab v3 using Keras functional API 270 – 273
Principal Component Analysis (PCA) 56, 548
probabilistic machine learning 19
mixed precision training 539 – 544
optimizing input pipeline 536 – 538
projecter.visualize_embeddings() function 549
prototyping deep learning models 10
pyramidal aggregation module 266
question answering with Hugging Face Transformers 483 – 509
defining DistilBERT model 495 – 502
defining and using tokenizer 488 – 493
from tokens to tf.data pipeline 493 – 494
randomly_crop_or_resize function 257, 259
recurrent neural networks. See RNNs
ReduceLROnPlateau callback 230 – 231
ReLU (rectified linear units) 53, 58, 223
return_sequences parameter unit 367
return_state parameter unit 368
RNNs (recurrent neural networks) 10, 14, 105 – 117, 134, 325, 402
predicting future CO2 values with trained model 115 – 117
RoBERT (recurrence over BERT) 640
samplewise_center parameter 197
samplewise_std_normalization parameter 197
save_pretrained() function 505
SBD (semantic boundary data set) 291
scale_to_z_score() function 572
cooking competition analogy 135 – 136
locality sensitive hashing in 644 – 645
masked self-attention layers 136 – 138
SelfAttentionLayer objects 141
defining final model 331 – 336
LSTM (long short-term memory) networks 326 – 331
sequence-to-sequence learning 387 – 452
defining inference model 423 – 430
improving model with attention 435 – 445
defining final model 440 – 443
implementing Bahdanau attention in TensorFlow 436 – 440
machine translation data 388 – 395
training and evaluating model 410 – 423
visualizing attention 445 – 451
writing English-German seq2seq machine translator 395 – 410
define TextVectorization layers for seq2seq model 400 – 401
defining decoder and final model 405 – 409
TextVectorization layer 398 – 400
small-scale structured data 12 – 13
evaluating and interpreting results 482 – 483
treating class imbalance in data 471 – 474
td.data.Dataset.map() function 255
profiling models to detect performance bottlenecks 529 – 544
mixed precision training 539 – 544
optimizing input pipeline 536 – 538
tracking and monitoring models with 517 – 526
using tf.summary to write custom metrics during model training 526 – 529
visualizing data with 512 – 516
visualizing word vectors with 544 – 550
tensorboard_plugin_profile package 532
tensorboard.plugins.projector object 549
Bahdanau attention in 436 – 440
final tf.data pipeline 264 – 265
optimizing tf.data pipelines 263 – 264
GRUs (gated recurrent units) 365 – 370
measuring quality of generated text 370 – 372
training and evaluating 372 – 374
monitoring and optimization 14 – 15
NLP (natural language processing) with 296 – 348
defining end-to-end NLP pipeline with TensorFlow 319 – 325
training and evaluating model 336 – 339
Python and TensorFlow 2 16 – 17
spam classification using BERT 470 – 483
evaluating and interpreting results 482 – 483
treating class imbalance in data 471 – 474
profiling models to detect performance bottlenecks 529 – 544
tracking and monitoring models with 517 – 526
using tf.summary to write custom metrics during model training 526 – 529
visualizing data with 512 – 516
creating complex natural language processing pipelines 13
implementing traditional machine learning models 12
manipulating and analyzing small-scale structured data 12 – 13
creating heavy-duty data pipelines 11 – 12
implementing models that run faster on optimized hardware 10 – 11
monitoring models during model training 11
productionizing models/serving on cloud 11
prototyping deep learning models 10
Keras model-building APIs 48 – 65
neural network-related computations 39 – 45
tensorflow-datasets package 75 – 78
tensorflow-dataset package 48, 75 – 78, 512
tensorflow_data_validation library 595
tensorflow.keras.layers.Dense() layer 140
tensorflow.keras.layers.experimental.preprocessing.TextVectorization layer 397
tensorflow.keras.layers.Flatten layer 104
tensorflow.keras.layers.MaxPool2D layer 103
tensorflow.keras.layers submodule 63
tensorflow_model_analysis library 602
tensorflow_transform library 572
tensor processing units (TPUs) 4
tensors 32 – 33
analyzing sequence length 315 – 316
analyzing vocabulary 313 – 315
generating with deep learning 365 – 370
measuring quality of generated 370 – 372
representing as numbers 120 – 122
splitting training, validation and testing data 309 – 313
text to words and then to numbers with Keras 316 – 319
texts_to_sequences() function 318
text_to_sequences() function 318
defining for seq2seq model 400 – 401
tf.argmax mathematical function 38
tf.argmin mathematical function 38
tf.cumsum mathematical function 38
tf.data API 6, 8, 66 – 72, 74 – 75
tf.data.Dataset.apply() function 324
tf.data.Dataset.batch() function 253, 261, 494
tf.data.Dataset.filter() function 321
tf.data.Dataset.flat_map() function 360, 362 – 363
tf.data.Dataset.from_generator() function 253, 494
tf.data.Dataset.from_tensor_slices() function 321, 324
tf.data.Dataset.map() function 255, 260, 362 – 363, 513
tf.data.Dataset objects 362, 526, 583
tf.data.Dataset.repeat() function 261
tf.data.Dataset.window() function 360, 362
tf.data.Dataset.zip() function 69
tf.data.experimental.bucket_by_sequence_length() function 323
tf.data.experimental.CsvDataset object 67
tf.data pipelines 252 – 255, 261, 263 – 264, 319, 331 – 332, 350, 360, 365, 487, 493 – 494, 531
tf_dataset_factory() function 584
tfdv.display_anomalies() function 595
tfdv.validate_statistics() function 595
tfdv.visualize_statistics() function 595
tf.feature_column-type objects 578
@tf.function decorator 25 – 26, 28, 587
TF_GPU_THREAD_COUNT variable 537
TF_GPU_THREAD_MODE=gpu_private variable 538
TF_GPU_THREAD_MODE variable 537
tf.io.parse_example() function 589
tf.keras.applications module 270
tf.keras.callbacks.EarlyStopping callback 210
tf.keras.initializers submodule 29
tf.keras.layers.AbstractRNNCell interface 436
tf.keras.layers.BatchNormalization() layers 527
tf.keras.layers.Conv2D layer 271
tf.keras.layers.DenseFeatures layer 582
tf.keras.layers.Input layers 582
tf.keras.layers.Lambda layer 172
tf.keras.layers.Masking layer 332
tf.keras.layers.RepeatVector(5) layer 410
tf.keras.layers.RepeatVector layer 410
tf.keras.metrics.Accuracy parent object’s 285
tf.keras.metrics.Mean class 371 – 372
tf.keras.metrics.Metric class 283 – 284
tf.keras.Model.fit() function 482
tf.keras.models.Model.fit() method 162
tf.keras.models.Model object 404
tf.keras.preprocessing.text.Tokenizer.fit_on_texts() function 318
tf.linalg.band_part() function 138
tf.math.top_k(batch_loss, n) function 293
tf.matmul(x,W)+b expression 23
tf-models-official library 475
tf.nn.convolution() function 42
tf.nn.convolution operation 96
tf.numpy_function operation 254
tf.ragged.constant() function 320
tf.RaggedTensor objects 320, 324, 360
tf.squeeze() function 40, 44, 261
tf.summary.<data type> object 514
tfx.components.CsvExampleGen object 560
TFX (TensorFlow-Extended) 554 – 614
deploying model and serving it through API 599 – 612
predicting with TensorFlow serving API 608 – 612
validating infrastructure 600 – 601
setting up Docker to serve trained model 596 – 599
training simple regression neural network with TFX Trainer API 576 – 596
defining Keras model 577 – 584
defining model training 584 – 586
training Keras model with TFX Trainer 589 – 596
writing data pipeline with 556 – 575
converting data to features 569 – 575
EDA (exploratory data analysis) 564 – 567
inferring schema from data 567 – 569
loading data from CSV files 560 – 564
TFX (TensorFlow-Extended) Trainer API 576 – 596
defining Keras model 577 – 584
defining model training 584 – 586
training Keras model with TFX Trainer 589 – 596
tiny-imagenet-200 data set 153 – 154, 232
ToBERT (Transformer over BERT) 640
tokenization 302, 316, 358 – 359, 488 – 494
TPUs (tensor processing units) 4
evaluating performance 149 – 192
Hugging Face Transformers, question answering with 502 – 505
NLP (natural language processing) 336 – 339
sequence-to-sequence learning 410 – 423
spam classification using BERT 482
TFX (TensorFlow-Extended) Trainer API 584 – 586
using tf.summary to write custom metrics during 526 – 529
train_model() function 421, 443, 527
transfer learning 233 – 238, 244
_transformed_name() function 575
transformers 123 – 146, 453 – 510, 639 – 645
cross-layer parameter sharing 643 – 644
factorization of embedding layer 643
sentence-order prediction instead of next sentence prediction 644
BART (bidirectional and auto-regressive Transformers) 640 – 642
encoder-decoder pattern 123 – 124
fully connected layer 139 – 141
GPT (generative pre-training) model 639 – 640
multi-head attention 138 – 139
question answering with Hugging Face Transformers 483 – 509
defining DistilBERT model 495 – 502
residuals and normalization 460 – 463
cooking competition analogy 135 – 136
masked self-attention layers 136 – 138
spam classification using BERT 463 – 483
creating virtual Python environment with Anaconda distribution 615 – 616
prerequisites for GPU support 616 – 618
unet_pretrained_encoder() function 638
Unix-based environment 615 – 618
creating virtual Python environment with Anaconda distribution (Ubuntu) 615 – 616
prerequisites for GPU support (Ubuntu) 616 – 618
update_char_to_token_positions_inplace() function 491
update_state() function 284 – 288, 372
val_accuracy validation accuracy 374
validating infrastructure 600 – 601
validation_split parameter 199
val_loss validation loss value 210
val_perlexity validation perplexity 374
Unix-based environment 615 – 616
Windows Environments 618 – 619
visualize_attention() function 448
width_shift_range parameter 197
Windows Environments 618 – 622
creating Virtual Python Environment (Anaconda) 618 – 619
prerequisites for GPU support 619 – 622
defining final model with 341 – 344
defining final model with word embeddings 341 – 344
training and evaluating model 344 – 346
18.222.111.24