À propos de WordPress
Site de WordPress-FR
Documentation
Forums de support
Vos retours
Connexion
Inscription
Rechercher
Passer au contenu
TensorFlow par BackProp
Formation à Tf
iris
Iris – #1
Iris – #2
Iris – #3
Iris – #4
Q & A
Certificat
Build, train NN
Use TensorFlow 2.x
Build, compile and train ML models
Preprocess data
Predict
Sequential models
Binary classification
Multi-class categorization
Plot loss and accuracy
Strategies to prevent overfitting
Pretrained models
Extract features from pre-trained models
Correct shape
Shape of test data
Ensure that you can match test data to the input shape of a neural network
Batch
Callbacks to trigger the end of training cycles
Use datasets from different sources
json and csv
Use datasets from tf.data.datasets
Ensure you can match output data of a neural network to specified input shape for test data
NLP
Build NLP
Prepare text
Binary categorization
Multi-class categorization
Use word embeddings
LSTMs
RNN and GRU layers
RNNS, LSTMs, GRUs and CNNs
Train LSTMs
Image classification
CNN with Conv2D and pooling
Process real-world image datasets
How to use convolutions
Use real-world images
Image augmentation
ImageDataGenerator
Understand how ImageDataGenerator labels images
Time series, sequences and predictions
Train, tune and use time series
Prepare data
Understand MAE
RNNs and CNNs
Trailing versus centred windows
TensorFlow for forecasting
Prepare features and labels
Identify and compensate for sequence bias
Adjust the learning rate
Search
Rechercher
Rechercher …
TensorFlow par BackProp
Search
Rechercher
Rechercher …
Rechercher
Rechercher …
Menu
Formation à Tf
iris
Iris – #1
Iris – #2
Iris – #3
Iris – #4
Q & A
Certificat
Build, train NN
Use TensorFlow 2.x
Build, compile and train ML models
Preprocess data
Predict
Sequential models
Binary classification
Multi-class categorization
Plot loss and accuracy
Strategies to prevent overfitting
Pretrained models
Extract features from pre-trained models
Correct shape
Shape of test data
Ensure that you can match test data to the input shape of a neural network
Batch
Callbacks to trigger the end of training cycles
Use datasets from different sources
json and csv
Use datasets from tf.data.datasets
Ensure you can match output data of a neural network to specified input shape for test data
NLP
Build NLP
Prepare text
Binary categorization
Multi-class categorization
Use word embeddings
LSTMs
RNN and GRU layers
RNNS, LSTMs, GRUs and CNNs
Train LSTMs
Image classification
CNN with Conv2D and pooling
Process real-world image datasets
How to use convolutions
Use real-world images
Image augmentation
ImageDataGenerator
Understand how ImageDataGenerator labels images
Time series, sequences and predictions
Train, tune and use time series
Prepare data
Understand MAE
RNNs and CNNs
Trailing versus centred windows
TensorFlow for forecasting
Prepare features and labels
Identify and compensate for sequence bias
Adjust the learning rate
Accueil
»
Time series, sequences and predictions
»
Identify and compensate for sequence bias
Identify and compensate for sequence bias
Parcourir les articles
Article précédent
Prepare features and labels
Article suivant
Adjust the learning rate dynamically in time series, sequence and prediction models
