Dinosaurus Island – Character level language model final - v3
1 - Problem Statement
1.1 - Dataset and Preprocessing
data = open('dinos.txt', 'r').read()
data= data.lower()
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)
print('There are %d total characters and %d unique characters in your data.' % (data_size, vocab_size)
1.2 - Overview of the model
2 - Building blocks of the model
2.1 - Clipping the gradients in the optimization loop
### GRADED FUNCTION: clip
def clip(gradients, maxValue):
'''
Clips the gradients' values between minimum and maximum.
Arguments:
gradients -- a dictionary containing the gradients "dWaa", "dWax", "dWya", "db", "dby"
maxValue -- everything above this number is set to this number, and everything less than -maxValue is set to -maxValue
Returns:
gradients -- a dictionary with the clipped gradients.
'''
dWaa, dWax, dWya, db, dby = gradients['dWaa'], gradients['dWax'], gradients['dWya'], gradients['db'], gradients['dby']
### START CODE HERE ###
# clip to mitigate exploding gradients, loop over [dWax, dWaa, dWya, db, dby]. (≈2 lines)
for gradient in [dWax, dWaa, dWya, db, dby]:
gradients=np.clip(gradient,a_min=-maxValue,a_max=maxValue,out=gradient)
### END CODE HERE ###
gradients = {"dWaa": dWaa, "dWax": dWax, "dWya": dWya, "db": db, "dby": dby}
return gradientsnp.random.seed(3)
dWax = np.random.randn(5,3)*10
dWaa = np.random.randn(5,5)*10
dWya = np.random.randn(2,5)*10
db = np.random.randn(5,1)*10
dby = np.random.randn(2,1)*10
gradients = {"dWax": dWax, "dWaa": dWaa, "dWya": dWya, "db": db, "dby": dby}
gradients = clip(gradients, 10)
print("gradients[\"dWaa\"][1][2] =", gradients["dWaa"][1][2])
print("gradients[\"dWax\"][3][1] =", gradients["dWax"][3][1])
print("gradients[\"dWya\"][1][2] =", gradients["dWya"][1][2])
print("gradients[\"db\"][4] =", gradients["db"][4])
print("gradients[\"dby\"][1] =", gradients["dby"][1])gradients[“dWaa”][1][2] = 10.0
gradients[“dWax”][3][1] = -10.0
gradients[“dWya”][1][2] = 0.29713815361
gradients[“db”][4] = [ 10.]
gradients[“dby”][1] = [ 8.45833407]
2.2 - Sampling
def sample(parameters, char_to_ix, seed):
### START CODE HERE ###
# Step 1: Create the one-hot vector x for the first character (initializing the sequence generation). (≈1 line)
x = np.zeros((vocab_size,1))
# Step 1': Initialize a_prev as zeros (≈1 line)
a_prev = np.zeros((n_a,1))
# Create an empty list of indices, this is the list which will contain the list of indices of the characters to generate (≈1 line)
indices = []
# Idx is a flag to detect a newline character, we initialize it to -1
idx = -1
# Loop over time-steps t. At each time-step, sample a character from a probability distribution and append
# its index to "indices". We'll stop if we reach 50 characters (which should be very unlikely with a well
# trained model), which helps debugging and prevents entering an infinite loop.
counter = 0
newline_character = char_to_ix['\n']
while (idx != newline_character and counter != 50):
# Step 2: Forward propagate x using the equations (1), (2) and (3)
a = np.tanh(np.dot(Wax,x)+np.dot(Waa,a_prev)+b)
z = np.dot(Wya,a)+by
y = softmax(z)
# for grading purposes
np.random.seed(counter+seed)
# Step 3: Sample the index of a character within the vocabulary from the probability distribution y
idx = np.random.choice(list(range(vocab_size)), p = y[:,0])
# Append the index to "indices"
indices.append(idx)
# Step 4: Overwrite the input character as the one corresponding to the sampled index.
x = np.zeros((vocab_size,1))
x[idx] = 1
# Update "a_prev" to be "a"
a_prev = a
# for grading purposes
seed += 1
counter +=1
### END CODE HERE ### if (counter == 50):
indices.append(char_to_ix['\n'])
return indices
np.random.seed(2)
_, n_a = 20, 100
Wax, Waa, Wya = np.random.randn(n_a, vocab_size), np.random.randn(n_a, n_a), np.random.randn(vocab_size, n_a)
b, by = np.random.randn(n_a, 1), np.random.randn(vocab_size, 1)
parameters = {"Wax": Wax, "Waa": Waa, "Wya": Wya, "b": b, "by": by}
indices = sample(parameters, char_to_ix, 0)
print("Sampling:")
print("list of sampled indices:", indices)
print("list of sampled characters:", [ix_to_char[i] for i in indices])Sampling:
list of sampled indices: [12, 17, 24, 14, 13, 9, 10, 22, 24, 6, 13, 11, 12, 6, 21, 15, 21, 14, 3, 2, 1, 21, 18, 24, 7, 25, 6, 25, 18, 10, 16, 2, 3, 8, 15, 12, 11, 7, 1, 12, 10, 2, 7, 7, 11, 5, 6, 12, 25, 0, 0]
list of sampled characters: [‘l’, ‘q’, ‘x’, ‘n’, ‘m’, ‘i’, ‘j’, ‘v’, ‘x’, ‘f’, ‘m’, ‘k’, ‘l’, ‘f’, ‘u’, ‘o’, ‘u’, ‘n’, ‘c’, ‘b’, ‘a’, ‘u’, ‘r’, ‘x’, ‘g’, ‘y’, ‘f’, ‘y’, ‘r’, ‘j’, ‘p’, ‘b’, ‘c’, ‘h’, ‘o’, ‘l’, ‘k’, ‘g’, ‘a’, ‘l’, ‘j’, ‘b’, ‘g’, ‘g’, ‘k’, ‘e’, ‘f’, ‘l’, ‘y’, ‘\n’, ‘\n’]
3 - Building the language model
3.1 - Gradient descent
# GRADED FUNCTION: optimize
def optimize(X, Y, a_prev, parameters, learning_rate = 0.01):### START CODE HERE ###
# Forward propagate through time (≈1 line)
loss, cache = rnn_forward(X, Y, a_prev, parameters)
# Backpropagate through time (≈1 line)
gradients, a = rnn_backward(X, Y, parameters, cache)
# Clip your gradients between -5 (min) and 5 (max) (≈1 line)
gradients = clip(gradients, maxValue = 5)
# Update parameters (≈1 line)
parameters = update_parameters(parameters, gradients, learning_rate)
### END CODE HERE ###
return loss, gradients, a[len(X)-1]
np.random.seed(1)
vocab_size, n_a = 27, 100
a_prev = np.random.randn(n_a, 1)
Wax, Waa, Wya = np.random.randn(n_a, vocab_size), np.random.randn(n_a, n_a), np.random.randn(vocab_size, n_a)
b, by = np.random.randn(n_a, 1), np.random.randn(vocab_size, 1)
parameters = {"Wax": Wax, "Waa": Waa, "Wya": Wya, "b": b, "by": by}
X = [12,3,5,11,22,3]
Y = [4,14,11,22,25, 26]
loss, gradients, a_last = optimize(X, Y, a_prev, parameters, learning_rate = 0.01)
print("Loss =", loss)
print("gradients[\"dWaa\"][1][2] =", gradients["dWaa"][1][2])
print("np.argmax(gradients[\"dWax\"]) =", np.argmax(gradients["dWax"]))
print("gradients[\"dWya\"][1][2] =", gradients["dWya"][1][2])
print("gradients[\"db\"][4] =", gradients["db"][4])
print("gradients[\"dby\"][1] =", gradients["dby"][1])
print("a_last[4] =", a_last[4])Loss = 126.503975722
gradients["dWaa"][1][2] = 0.194709315347
np.argmax(gradients["dWax"]) = 93
gradients["dWya"][1][2] = -0.007773876032
gradients["db"][4] = [-0.06809825]
gradients["dby"][1] = [ 0.01538192]
a_last[4] = [-1.]3.2 - Training the model
# GRADED FUNCTION: model
def model(data, ix_to_char, char_to_ix, num_iterations = 35000, n_a = 50, dino_names = 7, vocab_size = 27):
### START CODE HERE ###
# Use the hint above to define one training example (X,Y) (≈ 2 lines)
index = j % len(examples)
X = [None] + [char_to_ix[ch] for ch in examples[index]]
Y = X[1:] + [char_to_ix["\n"]]
# Perform one optimization step: Forward-prop -> Backward-prop -> Clip -> Update parameters
# Choose a learning rate of 0.01
curr_loss, gradients, a_prev = optimize(X, Y, a_prev, parameters, learning_rate = 0.01)
### END CODE HERE ###
# Use a latency trick to keep the loss smooth. It happens here to accelerate the training.
loss = smooth(loss, curr_loss)
# Every 2000 Iteration, generate "n" characters thanks to sample() to check if the model is learning properly
if j % 2000 == 0:
print('Iteration: %d, Loss: %f' % (j, loss) + '\n')
# The number of dinosaur names to print
seed = 0
for name in range(dino_names):
# Sample indices and print them
sampled_indices = sample(parameters, char_to_ix, seed)
print_sample(sampled_indices, ix_to_char)
seed += 1 # To get the same result for grading purposed, increment the seed by one.
print('\n')
return parametersIteration: 32000, Loss: 22.209473
Mawusaurus
Jica
Lustoia
Macaisaurus
Yusolenqtesaurus
Eeaeosaurus
Trnanatrax
Iteration: 34000, Loss: 22.396744
Mavptokekus
Ilabaisaurus
Itosaurus
Macaesaurus
Yrosaurus
Eiaeosaurus
Trodon
4 - Writing like Shakespeare
from __future__ import print_function
from keras.callbacks import LambdaCallback
from keras.models import Model, load_model, Sequential
from keras.layers import Dense, Activation, Dropout, Input, Masking
from keras.layers import LSTM
from keras.utils.data_utils import get_file
from keras.preprocessing.sequence import pad_sequences
from shakespeare_utils import *
import sys
import ioprint_callback = LambdaCallback(on_epoch_end=on_epoch_end)
model.fit(x, y, batch_size=128, epochs=1, callbacks=[print_callback])Epoch 1/1
31412/31412 [==============================] - 223s - loss: 2.5639
# Run this cell to try with different inputs without having to re-train the model
generate_output()
```Write the beginning of your poem, the Shakespeare machine will complete it. Your input is: i love this school
Here is your poem:
<div class="se-preview-section-delimiter"></div>
这里写代码片
“`
i love this school:
more brows ha dose wor base, my hobe,
ching is my matanhed of is of your, sills steens,
no hate wat i do by lew yes be spend's tomt,
aad hin onree wames to the pacy her with' formed,
whinge the of this kell live do commaces wite,
undacion when resers wears fame,
ever thou tore the thine the lise shemer.
for seof consing i be asdy bone.
o should such other genpleess wear,
shence my all in beer th
