深度学习笔记（40）：第五课第三周第二次作业
这一部分的实验我觉得挺跳跃的，突然就到语音识别了
时间重叠判定
# GRADED FUNCTION: is_overlapping
def is_overlapping(segment_time, previous_segments):
"""
Checks if the time of a segment overlaps with the times of existing segments.
Arguments:
segment_time -- a tuple of (segment_start, segment_end) for the new segment
previous_segments -- a list of tuples of (segment_start, segment_end) for the existing segments
Returns:
True if the time segment overlaps with any of the existing segments, False otherwise
"""
segment_start, segment_end = segment_time
### START CODE HERE ### (≈ 4 line)
# Step 1: Initialize overlap as a "False" flag. (≈ 1 line)
overlap = False
# Step 2: loop over the previous_segments start and end times.
# Compare start/end times and set the flag to True if there is an overlap (≈ 3 lines)
for previous_start, previous_end in previous_segments:
if segment_start >= previous_start and segment_start <= previous_end or segment_end >= previous_start and segment_end <= previous_end :
overlap = True
### END CODE HERE ###
return overlap
补齐
# GRADED FUNCTION: insert_ones
def insert_ones(y, segment_end_ms):
"""
Update the label vector y. The labels of the 50 output steps strictly after the end of the segment
should be set to 1. By strictly we mean that the label of segment_end_y should be 0 while, the
50 followinf labels should be ones.
Arguments:
y -- numpy array of shape (1, Ty), the labels of the training example
segment_end_ms -- the end time of the segment in ms
Returns:
y -- updated labels
"""
# duration of the background (in terms of spectrogram time-steps)
segment_end_y = int(segment_end_ms * Ty / 10000.0)
# Add 1 to the correct index in the background label (y)
### START CODE HERE ### (≈ 3 lines)
for i in range(segment_end_y+1, segment_end_y+51):
if i < Ty:
y[0, i] = 1
### END CODE HERE ###
return y
创建训练样例
# GRADED FUNCTION: create_training_example
def create_training_example(background, activates, negatives):
"""
Creates a training example with a given background, activates, and negatives.
Arguments:
background -- a 10 second background audio recording
activates -- a list of audio segments of the word "activate"
negatives -- a list of audio segments of random words that are not "activate"
Returns:
x -- the spectrogram of the training example
y -- the label at each time step of the spectrogram
"""
# Set the random seed
np.random.seed(18)
# Make background quieter
background = background - 20
### START CODE HERE ###
# Step 1: Initialize y (label vector) of zeros (≈ 1 line)
y = np.zeros((1, Ty))
# Step 2: Initialize segment times as empty list (≈ 1 line)
previous_segments = []
### END CODE HERE ###
# Select 0-4 random "activate" audio clips from the entire list of "activates" recordings
number_of_activates = np.random.randint(0, 5)
random_indices = np.random.randint(len(activates), size=number_of_activates)
random_activates = [activates[i] for i in random_indices]
### START CODE HERE ### (≈ 3 lines)
# Step 3: Loop over randomly selected "activate" clips and insert in background
for random_activate in random_activates:
# Insert the audio clip on the background
background, segment_time = insert_audio_clip(background, random_activate, previous_segments)
# Retrieve segment_start and segment_end from segment_time
segment_start, segment_end = segment_time
# Insert labels in "y"
y = insert_ones(y, segment_end)
### END CODE HERE ###
# Select 0-2 random negatives audio recordings from the entire list of "negatives" recordings
number_of_negatives = np.random.randint(0, 3)
random_indices = np.random.randint(len(negatives), size=number_of_negatives)
random_negatives = [negatives[i] for i in random_indices]
### START CODE HERE ### (≈ 2 lines)
# Step 4: Loop over randomly selected negative clips and insert in background
for random_negative in random_negatives:
# Insert the audio clip on the background
background, _ = insert_audio_clip(background, random_negative, previous_segments)
### END CODE HERE ###
# Standardize the volume of the audio clip
background = match_target_amplitude(background, -20.0)
# Export new training example
file_handle = background.export("train" + ".wav", format="wav")
print("File (train.wav) was saved in your directory.")
# Get and plot spectrogram of the new recording (background with superposition of positive and negatives)
x = graph_spectrogram("train.wav")
return x, y
keras模型搭建
# GRADED FUNCTION: model
def model(input_shape):
"""
Function creating the model's graph in Keras.
Argument:
input_shape -- shape of the model's input data (using Keras conventions)
Returns:
model -- Keras model instance
"""
X_input = Input(shape = input_shape)
### START CODE HERE ###
# Step 1: CONV layer (≈4 lines)
X = Conv1D(196, 15, strides=4)(X_input) # CONV1D
X = BatchNormalization()(X) # Batch normalization
X = Activation('relu')(X) # ReLu activation
X = Dropout(0.8)(X) # dropout (use 0.8)
# Step 2: First GRU Layer (≈4 lines)
X = GRU(units = 128, return_sequences=True)(X) # GRU (use 128 units and return the sequences)
X = Dropout(0.8)(X) # dropout (use 0.8)
X = BatchNormalization()(X) # Batch normalization
# Step 3: Second GRU Layer (≈4 lines)
X = GRU(units = 128, return_sequences=True)(X) # GRU (use 128 units and return the sequences)
X = Dropout(0.8)(X) # dropout (use 0.8)
X = BatchNormalization()(X) # Batch normalization
X = Dropout(0.8)(X) # dropout (use 0.8)
# Step 4: Time-distributed dense layer (≈1 line)
X = TimeDistributed(Dense(1, activation = "sigmoid"))(X) # time distributed (sigmoid)
### END CODE HERE ###
model = Model(inputs = X_input, outputs = X)
return model