Training settings
Please provide a valid training processor option
Audio training options
Neural network architecture
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, InputLayer, Dropout, Conv1D, Conv2D, Flatten, Reshape, MaxPooling1D, MaxPooling2D, AveragePooling2D, BatchNormalization, Permute, ReLU, Softmax
from tensorflow.keras.optimizers.legacy import Adam
from tensorflow.keras.callbacks import EarlyStopping
EPOCHS = args.epochs or 100
LEARNING_RATE = args.learning_rate or 0.005
# If True, non-deterministic functions (e.g. shuffling batches) are not used.
# This is False by default.
ENSURE_DETERMINISM = args.ensure_determinism
# this controls the batch size, or you can manipulate the tf.data.Dataset objects yourself
BATCH_SIZE = args.batch_size or 32
if not ENSURE_DETERMINISM:
train_dataset = train_dataset.shuffle(buffer_size=BATCH_SIZE*4)
train_dataset=train_dataset.batch(BATCH_SIZE, drop_remainder=False)
validation_dataset = validation_dataset.batch(BATCH_SIZE, drop_remainder=False)
# model architecture
model = Sequential()
model.add(Reshape((int(input_length / 40), 40), input_shape=(input_length, )))
model.add(Conv1D(8, kernel_size=3, padding='same', activation='relu'))
model.add(MaxPooling1D(pool_size=2, strides=2, padding='same'))
model.add(Dropout(0.25))
model.add(Conv1D(16, kernel_size=3, padding='same', activation='relu'))
model.add(MaxPooling1D(pool_size=2, strides=2, padding='same'))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(classes, name='y_pred', activation='softmax'))
# this controls the learning rate
opt = Adam(learning_rate=LEARNING_RATE, beta_1=0.9, beta_2=0.999)
callbacks.append(BatchLoggerCallback(
BATCH_SIZE,
train_sample_count,
epochs=EPOCHS,
ensure_determinism=ENSURE_DETERMINISM))
# apply early stopping
callbacks.append(EarlyStopping(
monitor='val_accuracy', # Monitor validation loss
min_delta=0.005, # Minimum change to qualify as an improvement
patience=15, # Stop after 10 epochs without improvement
verbose=1, # Print messages
restore_best_weights=True # Restore model weights from the epoch with the best value of the monitored quantity.
))
# train the neural network
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
model.fit(train_dataset, epochs=EPOCHS, validation_data=validation_dataset, verbose=2, callbacks=callbacks, class_weight=ei_tensorflow.training.get_class_weights(Y_train))
# Use this flag to disable per-channel quantization for a model.
# This can reduce RAM usage for convolutional models, but may have
# an impact on accuracy.
disable_per_channel_quantization = False
Input layer (3,960 features)
Reshape layer (40 columns)
1D conv / pool layer (8 filters, 3 kernel size, 1 layer)
Dropout (rate 0.25)
1D conv / pool layer (16 filters, 3 kernel size, 1 layer)
Dropout (rate 0.25)
Flatten layer
Output layer (2 classes)
Model
Model version: