Issues reshaping numpy array using Ellipsis

问题

I'm trying to replicate the following batch generator for a project. However I'm having issues reshaping my data. The goal of the function is to take an array of [6000,3000] and reshape it to shape [batch_size, 100,3000,1].

Functioning code I'm trying to replicate

def gen(dict_files, aug=False):
while True:
    record_name = random.choice(list(dict_files.keys()))
    batch_data = dict_files[record_name]
    all_rows = batch_data['x']

    for i in range(batch_size):
        start_index = random.choice(range(all_rows.shape[0]-WINDOW_SIZE))

        X = all_rows[start_index:start_index+WINDOW_SIZE, ...]
        Y = batch_data['y'][start_index:start_index+WINDOW_SIZE]

        X = np.expand_dims(X, 0)
        Y = np.expand_dims(Y, -1)
        Y = np.expand_dims(Y, 0)
        yield X, Y

gen outputs X, Y:

X.shape=(batch_size, 100, 3000, 1)
Y.shape=(batch_size, 100, 1)

My code:

Parameter definitions:

Features = array[6000,3000] & Labels = array[6000,]

def generator(features, labels, batch_size):

##Define batch shapes
X_train_batch = np.zeros((batch_size,100, 3000, 1))
y_train_batch = np.zeros((batch_size,100, 1))

while True:
    sample_index = random.choice(range(features.shape[0]))
    sample_data = features[sample_index]

    ##Generating training batches
    for i in range(batch_size):
        start_index = random.choice(range(sample_data.shape[0]-100))   #pick random start point in signal (of length 3000timesteps)

        X = sample_data[start_index:start_index + 100, ...] #record 100 timesteps in signal from rand start point
        Y = labels[start_index:start_index + 100] #Record classification of X
        #print(X.shape)                    #gives arrays of (100,), should be (100,3000)

        ##reshaping to input shape taken by model
        X = np.expand_dims(X, 0)
        Y = np.expand_dims(Y, -1)
        Y = np.expand_dims(Y, 0)

        ##Collecting samples into correct batch size
        #X_train_batch[i] = X
        #y_train_batch[i] = Y
        print(y_train_batch.shape) #gives (32,100,1) which is correct!
generator(features, labels, 32)

Can someone explain the function of the ellipsis('...') found hereX = all_rows[start_index:start_index+WINDOW_SIZE, ...]? From my understanding ellipsis places the 3000 timesteps of sample_data to give the output (100,3000), but I'm apparently not understanding something as I can't get the same behavior in my code.

Following on how could I replicate what gen is outputting with my code?

来源：https://stackoverflow.com/questions/60646209/issues-reshaping-numpy-array-using-ellipsis

标签

python

arrays

keras

numpy-ndarray

ellipsis