char_level_lang_model_sample.py

def sample(parameters, idx_to_chars, chars_to_idx, n):
    """
    Implements sampling of a squence of n characters characters length.
    The sampling will be based on the probability distribution output of RNN.
    """
    
    # Retrienve parameters, shapes, and vocab size
    Whh, Wxh, b = parameters["Whh"], parameters["Wxh"], parameters["b"]
    Why, c = parameters["Why"], parameters["c"]
    n_h, n_x = Wxh.shape
    vocab_size = c.shape[0]
    
    # Initialize a0 and x1 to zero vectors
    h_prev = np.zeros((n_h, 1))
    x = np.zeros((n_x, 1))
    # Initialize empty sequence
    indices = []
    idx = -1
    counter = 0
    while (counter <= n and idx != chars_to_idx["\n"]):
        # Fwd propagation
        h = np.tanh(np.dot(Whh, h_prev) + np.dot(Wxh, x) + b)
        o = np.dot(Why, h) + c
        probs = softmax(o)
        
        # Sample the index of the character using generated probs distribution
        idx = np.random.choice(vocab_size, p=probs.ravel())
        
        # Get the character of the sampled index
        char = idx_to_chars[idx]
    
        # Add the char to the sequence
        indices.append(idx)
        
        # Update a_prev and x
        h_prev = np.copy(h)
        x = np.zeros((n_x, 1))
        x[idx] = 1
        
        counter += 1
    sequence = "".join([idx_to_chars[idx] for idx in indices if idx != 0])
    return sequence