def probability_plot(probabilities,
selected_sentence,
dataset,
ploting_path,
top_n_probabilities=20,
max_length=120):
# Pyplot options
fig, ax = plt.subplots()
ax.set_axis_off()
tb = Table(ax, bbox=[0, 0, 1, 1])
ncols = probabilities.shape[0]
width, height = 1.0 / (ncols + 1), 1.0 / (top_n_probabilities + 1)
# Truncate the time
selected_sentence = selected_sentence[:max_length]
probabilities = probabilities[:max_length]
# Sort the frequencies
sorted_indices = np.argsort(probabilities, axis=1)
probabilities = probabilities[
np.repeat(np.arange(probabilities.shape[0])[:, None],
probabilities.shape[1],
axis=1), sorted_indices][:, ::-1]
# Truncate the probabilities
probabilities = probabilities[:, :top_n_probabilities]
for (i, j), _ in np.ndenumerate(probabilities):
tb.add_cell(j + 1,
i,
height,
width,
text=unicode(str(
conv_into_char(sorted_indices[i, j, 1], dataset)[0]),
errors='ignore'),
loc='center',
facecolor=(1, 1 - probabilities[i, j, 0],
1 - probabilities[i, j, 0]))
for i, char in enumerate(selected_sentence):
tb.add_cell(0,
i,
height,
width,
text=unicode(char, errors='ignore'),
loc='center',
facecolor='green')
ax.add_table(tb)
plt.savefig(ploting_path)
def probability_plot(probabilities, selected_sentence, dataset, ploting_path,
top_n_probabilities=20, max_length=120):
# Pyplot options
fig, ax = plt.subplots()
ax.set_axis_off()
tb = Table(ax, bbox=[0, 0, 1, 1])
ncols = probabilities.shape[0]
width, height = 1.0 / (ncols + 1), 1.0 / (top_n_probabilities + 1)
# Truncate the time
selected_sentence = selected_sentence[:max_length]
probabilities = probabilities[:max_length]
# Sort the frequencies
sorted_indices = np.argsort(probabilities, axis=1)
probabilities = probabilities[
np.repeat(np.arange(probabilities.shape[0])[
:, None], probabilities.shape[1], axis=1),
sorted_indices][:, ::-1]
# Truncate the probabilities
probabilities = probabilities[:, :top_n_probabilities]
for (i, j), _ in np.ndenumerate(probabilities):
tb.add_cell(j + 1, i, height, width,
text=unicode(str(conv_into_char(sorted_indices[i, j, 1],
dataset)[0]),
errors='ignore'),
loc='center',
facecolor=(1,
1 - probabilities[i, j, 0],
1 - probabilities[i, j, 0]))
for i, char in enumerate(selected_sentence):
tb.add_cell(0, i, height, width,
text=unicode(char, errors='ignore'),
loc='center', facecolor='green')
ax.add_table(tb)
plt.savefig(ploting_path)
def plot(what, train_stream, compiled, args):
# states
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][0: args.visualize_length, 0:1]
values = compiled(init_)
layers = len(values)
time = values[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
for d in range(layers):
# Change the subplot
plt.subplot(layers, 1, d + 1)
# print only 5 values of the hiddenstate
for j in range(10):
plt.plot(np.arange(time), values[d][:, 0, j])
# plt.plot(
# np.arange(time), np.mean(np.abs(values[d][:, 0, :]), axis=1))
# Add ticks for xaxis
plt.xticks(range(args.visualize_length), ticks)
# Fancy options
plt.grid(True)
plt.title(what + "_of_layer_" + str(d))
plt.tight_layout()
# Either plot on the current display or save the plot into a file
if args.local:
plt.show()
else:
plt.savefig(
args.save_path + "/visualize_" + what + '_' + str(num) + ".png")
logger.info("Figure \"visualize_" + what + '_' + str(num) +
".png\" saved at directory: " + args.save_path)
def plot(what, train_stream, compiled, args):
# states
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][0:args.visualize_length, 0:1]
values = compiled(init_)
layers = len(values)
time = values[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
for d in range(layers):
# Change the subplot
plt.subplot(layers, 1, d + 1)
# print only 5 values of the hiddenstate
for j in range(10):
plt.plot(np.arange(time), values[d][:, 0, j])
# plt.plot(
# np.arange(time), np.mean(np.abs(values[d][:, 0, :]), axis=1))
# Add ticks for xaxis
plt.xticks(range(args.visualize_length), ticks)
# Fancy options
plt.grid(True)
plt.title(what + "_of_layer_" + str(d))
plt.tight_layout()
# Either plot on the current display or save the plot into a file
if args.local:
plt.show()
else:
plt.savefig(args.save_path + "/visualize_" + what + '_' +
str(num) + ".png")
logger.info("Figure \"visualize_" + what + '_' + str(num) +
".png\" saved at directory: " + args.save_path)
def visualize_generate(cost, hidden_states, updates,
train_stream, valid_stream,
args):
use_indices = has_indices(args.dataset)
output_size = get_output_size(args.dataset)
# Get presoft and its computation graph
filter_presoft = VariableFilter(theano_name="presoft")
presoft = filter_presoft(ComputationGraph(cost).variables)[0]
cg = ComputationGraph(presoft)
# Handle the theano shared variables that allow carrying the hidden
# state
givens, f_updates = carry_hidden_state(updates, 1, reset=not(use_indices))
if args.hide_all_except is not None:
pass
# Compile the theano function
compiled = theano.function(inputs=cg.inputs, outputs=presoft,
givens=givens, updates=f_updates)
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
all_ = next(epoch_iterator)
all_sequence = all_[0][:, 0:1]
targets = all_[1][:, 0:1]
# In the case of characters and text
if use_indices:
init_ = all_sequence[:args.initial_text_length]
# Time X Features
probability_array = np.zeros((0, output_size))
generated_text = init_
for i in range(args.generated_text_lenght):
presoft = compiled(generated_text)
# Get the last value of presoft
last_presoft = presoft[-1:, 0, :]
# Compute the probability distribution
probabilities = softmax(last_presoft)
# Store it in the list
probability_array = np.vstack([probability_array,
probabilities])
# Sample a character out of the probability distribution
argmax = (args.softmax_sampling == 'argmax')
last_output_sample = sample(probabilities, argmax)[:, None, :]
# Concatenate the new value to the text
generated_text = np.vstack(
[generated_text, last_output_sample])
ploting_path = None
if args.save_path is not None:
ploting_path = os.path.join(
args.save_path, 'prob_plot.png')
# Convert with real characters
whole_sentence = conv_into_char(
generated_text[:, 0], args.dataset)
initial_sentence = whole_sentence[:init_.shape[0]]
selected_sentence = whole_sentence[init_.shape[0]:]
logger.info(''.join(initial_sentence) + '...')
logger.info(''.join(whole_sentence))
if ploting_path is not None:
probability_plot(probability_array, selected_sentence,
args.dataset, ploting_path)
# In the case of sine wave dataset for example
else:
presoft = compiled(all_sequence)
time_plot = presoft.shape[0] - 1
plt.plot(np.arange(time_plot),
targets[:time_plot, 0, 0],
label="target")
plt.plot(np.arange(time_plot), presoft[:time_plot, 0, 0],
label="predicted")
plt.legend()
plt.grid(True)
plt.show()
def do(self, *args):
# init is TIME X 1
# This is because in interactive mode,
# self.main_loop.epoch_iterator is not accessible.
if self.interactive_mode:
# TEMPORARY HACK
iterator = self.main_loop.data_stream.get_epoch_iterator()
all_sequence = next(iterator)[0][:, 0:1]
else:
iterator = self.main_loop.epoch_iterator
all_sequence = next(iterator)["features"][:, 0:1]
init_ = all_sequence[:self.init_length]
# Time X Features
probability_array = np.zeros((0, self.output_size))
generated_text = init_
logger.info("\nGeneration:")
for i in range(self.generation_length):
presoft = self.generate(generated_text)[0]
# Get the last value of presoft
last_presoft = presoft[-1:, 0, :]
if self.has_indices:
# Compute the probability distribution
probabilities = softmax(last_presoft)
# Store it in the list
probability_array = np.vstack([probability_array,
probabilities])
# Sample a character out of the probability distribution
argmax = (self.softmax_sampling == 'argmax')
last_output_sample = sample(probabilities, argmax)[:, None, :]
else:
last_output_sample = last_presoft[:, None, :]
# Concatenate the new value to the text
generated_text = np.vstack([generated_text, last_output_sample])
# In the case of characters and text
if self.has_indices:
# Convert with real characters
whole_sentence = conv_into_char(generated_text[:, 0], self.dataset)
initial_sentence = whole_sentence[:init_.shape[0]]
selected_sentence = whole_sentence[init_.shape[0]:]
logger.info(''.join(initial_sentence) + '...')
logger.info(''.join(whole_sentence))
if self.ploting_path is not None:
probability_plot(probability_array, selected_sentence,
self.dataset, self.ploting_path)
# In the case of sine wave dataset for example
else:
time_plot = min([all_sequence.shape[0], generated_text.shape[0]])
plt.plot(np.arange(time_plot), all_sequence[:time_plot, 0, 0],
label="target")
plt.plot(np.arange(time_plot), generated_text[:time_plot, 0, 0],
label="predicted")
plt.legend()
plt.show()
def visualize_gates_lstm(gate_values, hidden_states, updates,
train_stream, valid_stream,
args):
in_gates = gate_values["in_gates"]
out_gates = gate_values["out_gates"]
forget_gates = gate_values["forget_gates"]
# Handle the theano shared variables that allow carrying the hidden state
givens, f_updates = carry_hidden_state(updates, 1,
not(has_indices(args.dataset)))
generate_in = theano.function(inputs=ComputationGraph(in_gates).inputs,
outputs=in_gates,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
generate_out = theano.function(inputs=ComputationGraph(out_gates).inputs,
outputs=out_gates,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
generate_forget = theano.function(inputs=ComputationGraph(forget_gates).inputs,
outputs=forget_gates,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
# Generate
epoch_iterator = valid_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][0: args.visualize_length, 0:1]
last_output_in = generate_in(init_)
last_output_out = generate_out(init_)
last_output_forget = generate_forget(init_)
layers = len(last_output_in)
time = last_output_in[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
for i in range(layers):
plt.subplot(3, layers, 1 + i)
plt.plot(np.arange(time), np.mean(
np.abs(last_output_in[i][:, 0, :]), axis=1))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("in_gate of layer " + str(i))
plt.subplot(3, layers, layers + 1 + i)
plt.plot(np.arange(time), np.mean(
np.abs(last_output_out[i][:, 0, :]), axis=1))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("out_gate of layer " + str(i))
plt.subplot(3, layers, 2 * layers + 1 + i)
plt.plot(np.arange(time), np.mean(
np.abs(last_output_forget[i][:, 0, :]), axis=1))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("forget_gate of layer " + str(i))
if args.local:
plt.show()
else:
plt.savefig(
args.save_path + "/visualize_gates_" + str(num) + ".png")
logger.info("Figure \"visualize_gates_" + str(num) +
".png\" saved at directory: " + args.save_path)
def visualize_generate(cost, hidden_states, updates,
train_stream, valid_stream,
args):
use_indices = has_indices(args.dataset)
output_size = get_output_size(args.dataset)
# Get presoft and its computation graph
filter_presoft = VariableFilter(theano_name="presoft")
presoft = filter_presoft(ComputationGraph(cost).variables)[0]
cg = ComputationGraph(presoft)
# Handle the theano shared variables that allow carrying the hidden
# state
givens, f_updates = carry_hidden_state(updates, 1, reset=not(use_indices))
# Compile the theano function
compiled = theano.function(inputs=cg.inputs, outputs=presoft,
givens=givens, updates=f_updates)
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
all_ = next(epoch_iterator)
all_sequence = all_[0][:, 0:1]
targets = all_[1][:, 0:1]
# In the case of characters and text
if use_indices:
init_ = all_sequence[:args.initial_text_length]
# Time X Features
probability_array = np.zeros((0, output_size))
generated_text = init_
for i in range(args.generated_text_lenght):
presoft = compiled(generated_text)
# Get the last value of presoft
last_presoft = presoft[-1:, 0, :]
# Compute the probability distribution
probabilities = softmax(last_presoft)
# Store it in the list
probability_array = np.vstack([probability_array,
probabilities])
# Sample a character out of the probability distribution
argmax = (args.softmax_sampling == 'argmax')
last_output_sample = sample(probabilities, argmax)[:, None, :]
# Concatenate the new value to the text
generated_text = np.vstack(
[generated_text, last_output_sample])
ploting_path = None
if args.save_path is not None:
ploting_path = os.path.join(
args.save_path, 'prob_plot.png')
# Convert with real characters
whole_sentence = conv_into_char(
generated_text[:, 0], args.dataset)
initial_sentence = whole_sentence[:init_.shape[0]]
selected_sentence = whole_sentence[init_.shape[0]:]
logger.info(''.join(initial_sentence) + '...')
logger.info(''.join(whole_sentence))
if ploting_path is not None:
probability_plot(probability_array, selected_sentence,
args.dataset, ploting_path)
# In the case of sine wave dataset for example
else:
presoft = compiled(all_sequence)
time_plot = presoft.shape[0] - 1
plt.plot(np.arange(time_plot),
targets[:time_plot, 0, 0],
label="target")
plt.plot(np.arange(time_plot), presoft[:time_plot, 0, 0],
label="predicted")
plt.legend()
plt.grid(True)
plt.show()
def visualize_gradients(hidden_states, updates,
train_stream, valid_stream,
args):
# Get all the hidden_states
filter_states = VariableFilter(theano_name_regex="hidden_state_.*")
all_states = filter_states(hidden_states)
all_states = sorted(all_states, key=lambda var: var.name[-1])
# Get all the hidden_cells
filter_cells = VariableFilter(theano_name_regex="hidden_cell_.*")
all_cells = filter_cells(hidden_states)
all_cells = sorted(all_cells, key=lambda var: var.name[-1])
# Get the variable on which we compute the gradients
filter_pre_rnn = VariableFilter(theano_name_regex="pre_rnn.*")
wrt = filter_pre_rnn(ComputationGraph(hidden_states).variables)
wrt = sorted(wrt, key=lambda var: var.name[-1])
len_wrt = len(wrt)
# We have wrt = [pre_rnn] or [pre_rnn_0, pre_rnn_1, ...]
# Assertion part
assert len(all_states) == args.layers
assert len(all_cells) == (args.layers * (args.rnn_type == "lstm"))
if args.skip_connections:
assert len_wrt == args.layers
else:
assert len_wrt == 1
# Comupute the gradients of states or cells
if args.rnn_type == "lstm" and args.visualize_cells:
states = all_cells
else:
states = all_states
logger.info("The computation of the gradients has started")
gradients = []
for i, state in enumerate(states):
gradients.extend(
tensor.grad(tensor.mean(tensor.abs_(
state[-1, 0, :])), wrt[:i + 1]))
# -1 indicates that gradient is gradient of the last time-step.c
logger.info("The computation of the gradients is done")
# Handle the theano shared variables that allow carrying the hidden state
givens, f_updates = carry_hidden_state(updates, 1,
reset=not(has_indices(args.dataset)))
# Compile the function
logger.info("The compilation of the function has started")
compiled = theano.function(inputs=ComputationGraph(states).inputs,
outputs=gradients,
givens=givens, updates=f_updates,
mode=Mode(optimizer='fast_compile'))
logger.info("The function has been compiled")
# Generate
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][
0: args.visualize_length, 0:1]
# [layers * len_wrt] [Time, 1, Hidden_dim]
gradients = compiled(init_)
if args.skip_connections:
assert len(gradients) == (args.layers * (args.layers + 1)) / 2
else:
assert len(gradients) == args.layers
time = gradients[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
# One row subplot for each variable wrt which we are computing
# the gradients
for var in range(len_wrt):
plt.subplot(len_wrt, 1, var + 1)
for d in range(args.layers - var):
plt.plot(
np.arange(time),
np.mean(np.abs(gradients[d][:, 0, :]), axis=1),
label="layer " + str(d + var))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.yscale('log')
axes = plt.gca()
axes.set_ylim([5e-20, 5e-1])
plt.title("gradients plotting w.r.t pre_rrn" + str(var))
plt.legend()
plt.tight_layout()
if args.local:
plt.show()
else:
plt.savefig(
args.save_path + "/visualize_gradients_" + str(num) + ".png")
logger.info("Figure \"visualize_gradients_" + str(num) +
".png\" saved at directory: " + args.save_path)
def visualize_presoft(cost, hidden_states, updates,
train_stream, valid_stream,
args):
filter_presoft = VariableFilter(theano_name="presoft")
presoft = filter_presoft(ComputationGraph(cost).variables)[0]
# Get all the hidden_states
filter_states = VariableFilter(theano_name_regex="hidden_state_.*")
all_states = filter_states(hidden_states)
all_states = sorted(all_states, key=lambda var: var.name[-1])
# Assertion part
assert len(all_states) == args.layers
logger.info("The computation of the gradients has started")
gradients = []
for i in range(args.visualize_length - args.context):
gradients.extend(
tensor.grad(tensor.mean(tensor.abs_(presoft[i, 0, :])),
all_states))
logger.info("The computation of the gradients is done")
# Handle the theano shared variables that allow carrying the hidden state
givens, f_updates = carry_hidden_state(updates, 1,
not(has_indices(args.dataset)))
# Compile the function
logger.info("The compilation of the function has started")
compiled = theano.function(inputs=ComputationGraph(presoft).inputs,
outputs=gradients,
givens=givens, updates=f_updates,
mode=Mode(optimizer='fast_compile'))
logger.info("The function has been compiled")
# Generate
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][
0: args.visualize_length, 0:1]
hidden_state = compiled(init_)
value_of_layer = {}
for d in range(args.layers):
value_of_layer[d] = 0
for i in range(len(hidden_state) / args.layers):
for d in range(args.layers):
value_of_layer[d] += hidden_state[d + i * args.layers]
time = hidden_state[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
for d in range(args.layers):
plt.plot(
np.arange(time),
np.mean(np.abs(value_of_layer[d][:, 0, :]), axis=1),
label="Layer " + str(d))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("hidden_state_of_layer_" + str(d))
plt.legend()
plt.tight_layout()
if args.local:
plt.show()
else:
plt.savefig(
args.save_path + "/visualize_presoft_" + str(num) + ".png")
logger.info("Figure \"visualize_presoft_" + str(num) +
".png\" saved at directory: " + args.save_path)
def do(self, *args):
# init is TIME X 1
# This is because in interactive mode,
# self.main_loop.epoch_iterator is not accessible.
if self.interactive_mode:
# TEMPORARY HACK
iterator = self.main_loop.data_stream.get_epoch_iterator()
all_sequence = next(iterator)[0][:, 0:1]
else:
iterator = self.main_loop.epoch_iterator
all_sequence = next(iterator)["features"][:, 0:1]
init_ = all_sequence[:self.init_length]
# Time X Features
probability_array = np.zeros((0, self.output_size))
generated_text = init_
logger.info("\nGeneration:")
for i in range(self.generation_length):
presoft = self.generate(generated_text)[0]
# Get the last value of presoft
last_presoft = presoft[-1:, 0, :]
if self.has_indices:
# Compute the probability distribution
probabilities = softmax(last_presoft)
# Store it in the list
probability_array = np.vstack(
[probability_array, probabilities])
# Sample a character out of the probability distribution
argmax = (self.softmax_sampling == 'argmax')
last_output_sample = sample(probabilities, argmax)[:, None, :]
else:
last_output_sample = last_presoft[:, None, :]
# Concatenate the new value to the text
generated_text = np.vstack([generated_text, last_output_sample])
# In the case of characters and text
if self.has_indices:
# Convert with real characters
whole_sentence = conv_into_char(generated_text[:, 0], self.dataset)
initial_sentence = whole_sentence[:init_.shape[0]]
selected_sentence = whole_sentence[init_.shape[0]:]
logger.info(''.join(initial_sentence) + '...')
logger.info(''.join(whole_sentence))
if self.ploting_path is not None:
probability_plot(probability_array, selected_sentence,
self.dataset, self.ploting_path)
# In the case of sine wave dataset for example
else:
time_plot = min([all_sequence.shape[0], generated_text.shape[0]])
plt.plot(np.arange(time_plot),
all_sequence[:time_plot, 0, 0],
label="target")
plt.plot(np.arange(time_plot),
generated_text[:time_plot, 0, 0],
label="predicted")
plt.legend()
plt.show()
def visualize_jacobian(hidden_states, updates,
train_stream, valid_stream,
args):
# Get all the hidden_states
all_states = [
var for var in hidden_states if re.match("hidden_state_.*", var.name)]
all_states = sorted(all_states, key=lambda var: var.name[-1])
# Get all the hidden_cells
all_cells = [var for var in hidden_states if re.match(
"hidden_cell_.*", var.name)]
all_cells = sorted(all_cells, key=lambda var: var.name[-1])
# Get the variable on which we compute the gradients
variables = ComputationGraph(hidden_states).variables
wrt = [
var for var in variables if
(var.name is not None) and (re.match("pre_rnn.*", var.name))]
wrt = sorted(wrt, key=lambda var: var.name[-1])
len_wrt = len(wrt)
# We have wrt = [pre_rnn] or [pre_rnn_0, pre_rnn_1, ...]
# Assertion part
assert len(all_states) == args.layers
assert len(all_cells) == (args.layers * (args.rnn_type == "lstm"))
if args.skip_connections:
assert len_wrt == args.layers
else:
assert len_wrt == 1
# Comupute the gradients of states or cells
if args.rnn_type == "lstm" and args.visualize_cells:
states = all_cells
else:
states = all_states
logger.info("The computation of the gradients has started")
gradients = []
for i, state in enumerate(states):
gradients.append(
tensor.grad(tensor.mean(tensor.abs_(
state[-1])), state))
# -1 indicates that gradient is gradient of the last time-step.c
logger.info("The computation of the gradients is done")
# Handle the theano shared variables for the state
state_vars = [theano.shared(
v[0:1, :].zeros_like().eval(), v.name + '-gen')
for v, _ in updates]
givens = [(v, x) for (v, _), x in zip(updates, state_vars)]
f_updates = [(x, upd) for x, (_, upd) in zip(state_vars, updates)]
# Compile the function
logger.info("The compilation of the function has started")
compiled = theano.function(inputs=ComputationGraph(states).inputs,
outputs=gradients,
givens=givens, updates=f_updates,
mode=Mode(optimizer='fast_compile'))
logger.info("The function has been compiled")
import ipdb
ipdb.set_trace()
# Generate
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][
0: args.visualize_length, 0:1]
# [layers * len_wrt] [Time, 1, Hidden_dim]
gradients = compiled(init_)
time = gradients[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
# One row subplot for each variable wrt which we are computing
# the gradients
for var in range(len_wrt):
plt.subplot(len_wrt, 1, var + 1)
for d in range(args.layers - var):
plt.plot(
np.arange(time),
np.mean(np.abs(gradients[d][:, 0, :]), axis=1),
label="layer " + str(d + var))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.yscale('log')
axes = plt.gca()
axes.set_ylim([5e-20, 5e-1])
plt.title("gradients plotting w.r.t pre_rrn" + str(var))
plt.legend()
plt.tight_layout()
if args.local:
plt.show()
else:
plt.savefig(
args.save_path + "/visualize_jacobian_" + str(num) + ".png")
logger.info("Figure \"visualize_jacobian_" + str(num) +
".png\" saved at directory: " + args.save_path)
def visualize_presoft(cost, hidden_states, updates, train_stream, valid_stream,
args):
filter_presoft = VariableFilter(theano_name="presoft")
presoft = filter_presoft(ComputationGraph(cost).variables)[0]
# Get all the hidden_states
filter_states = VariableFilter(theano_name_regex="hidden_state_.*")
all_states = filter_states(hidden_states)
all_states = sorted(all_states, key=lambda var: var.name[-1])
# Assertion part
assert len(all_states) == args.layers
logger.info("The computation of the gradients has started")
gradients = []
for i in range(args.visualize_length - args.context):
gradients.extend(
tensor.grad(tensor.mean(tensor.abs_(presoft[i, 0, :])),
all_states))
logger.info("The computation of the gradients is done")
# Handle the theano shared variables that allow carrying the hidden state
givens, f_updates = carry_hidden_state(updates, 1,
not (has_indices(args.dataset)))
# Compile the function
logger.info("The compilation of the function has started")
compiled = theano.function(inputs=ComputationGraph(presoft).inputs,
outputs=gradients,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
logger.info("The function has been compiled")
# Generate
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][0:args.visualize_length, 0:1]
hidden_state = compiled(init_)
value_of_layer = {}
for d in range(args.layers):
value_of_layer[d] = 0
for i in range(len(hidden_state) / args.layers):
for d in range(args.layers):
value_of_layer[d] += hidden_state[d + i * args.layers]
time = hidden_state[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
for d in range(args.layers):
plt.plot(np.arange(time),
np.mean(np.abs(value_of_layer[d][:, 0, :]), axis=1),
label="Layer " + str(d))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("hidden_state_of_layer_" + str(d))
plt.legend()
plt.tight_layout()
if args.local:
plt.show()
else:
plt.savefig(args.save_path + "/visualize_presoft_" + str(num) +
".png")
logger.info("Figure \"visualize_presoft_" + str(num) +
".png\" saved at directory: " + args.save_path)
def visualize_gradients(hidden_states, updates, train_stream, valid_stream,
args):
# Get all the hidden_states
filter_states = VariableFilter(theano_name_regex="hidden_state_.*")
all_states = filter_states(hidden_states)
all_states = sorted(all_states, key=lambda var: var.name[-1])
# Get all the hidden_cells
filter_cells = VariableFilter(theano_name_regex="hidden_cell_.*")
all_cells = filter_cells(hidden_states)
all_cells = sorted(all_cells, key=lambda var: var.name[-1])
# Get the variable on which we compute the gradients
filter_pre_rnn = VariableFilter(theano_name_regex="pre_rnn.*")
wrt = filter_pre_rnn(ComputationGraph(hidden_states).variables)
wrt = sorted(wrt, key=lambda var: var.name[-1])
len_wrt = len(wrt)
# We have wrt = [pre_rnn] or [pre_rnn_0, pre_rnn_1, ...]
# Assertion part
assert len(all_states) == args.layers
assert len(all_cells) == (args.layers * (args.rnn_type == "lstm"))
if args.skip_connections:
assert len_wrt == args.layers
else:
assert len_wrt == 1
# Comupute the gradients of states or cells
if args.rnn_type == "lstm" and args.visualize_cells:
states = all_cells
else:
states = all_states
logger.info("The computation of the gradients has started")
gradients = []
for i, state in enumerate(states):
gradients.extend(
tensor.grad(tensor.mean(tensor.abs_(state[-1, 0, :])),
wrt[:i + 1]))
# -1 indicates that gradient is gradient of the last time-step.c
logger.info("The computation of the gradients is done")
# Handle the theano shared variables that allow carrying the hidden state
givens, f_updates = carry_hidden_state(
updates, 1, reset=not (has_indices(args.dataset)))
# Compile the function
logger.info("The compilation of the function has started")
compiled = theano.function(inputs=ComputationGraph(states).inputs,
outputs=gradients,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
logger.info("The function has been compiled")
# Generate
epoch_iterator = train_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][0:args.visualize_length, 0:1]
# [layers * len_wrt] [Time, 1, Hidden_dim]
gradients = compiled(init_)
if args.skip_connections:
assert len(gradients) == (args.layers * (args.layers + 1)) / 2
else:
assert len(gradients) == args.layers
time = gradients[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
# One row subplot for each variable wrt which we are computing
# the gradients
for var in range(len_wrt):
plt.subplot(len_wrt, 1, var + 1)
for d in range(args.layers - var):
plt.plot(np.arange(time),
np.mean(np.abs(gradients[d][:, 0, :]), axis=1),
label="layer " + str(d + var))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.yscale('log')
axes = plt.gca()
axes.set_ylim([5e-20, 5e-1])
plt.title("gradients plotting w.r.t pre_rrn" + str(var))
plt.legend()
plt.tight_layout()
if args.local:
plt.show()
else:
plt.savefig(args.save_path + "/visualize_gradients_" + str(num) +
".png")
logger.info("Figure \"visualize_gradients_" + str(num) +
".png\" saved at directory: " + args.save_path)
def visualize_gates_lstm(gate_values, hidden_states, updates, train_stream,
valid_stream, args):
in_gates = gate_values["in_gates"]
out_gates = gate_values["out_gates"]
forget_gates = gate_values["forget_gates"]
# Handle the theano shared variables that allow carrying the hidden state
givens, f_updates = carry_hidden_state(updates, 1,
not (has_indices(args.dataset)))
generate_in = theano.function(inputs=ComputationGraph(in_gates).inputs,
outputs=in_gates,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
generate_out = theano.function(inputs=ComputationGraph(out_gates).inputs,
outputs=out_gates,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
generate_forget = theano.function(
inputs=ComputationGraph(forget_gates).inputs,
outputs=forget_gates,
givens=givens,
updates=f_updates,
mode=Mode(optimizer='fast_compile'))
# Generate
epoch_iterator = valid_stream.get_epoch_iterator()
for num in range(10):
init_ = next(epoch_iterator)[0][0:args.visualize_length, 0:1]
last_output_in = generate_in(init_)
last_output_out = generate_out(init_)
last_output_forget = generate_forget(init_)
layers = len(last_output_in)
time = last_output_in[0].shape[0]
if has_indices(args.dataset):
ticks = tuple(conv_into_char(init_[:, 0], args.dataset))
else:
ticks = tuple(np.arange(time))
for i in range(layers):
plt.subplot(3, layers, 1 + i)
plt.plot(np.arange(time),
np.mean(np.abs(last_output_in[i][:, 0, :]), axis=1))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("in_gate of layer " + str(i))
plt.subplot(3, layers, layers + 1 + i)
plt.plot(np.arange(time),
np.mean(np.abs(last_output_out[i][:, 0, :]), axis=1))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("out_gate of layer " + str(i))
plt.subplot(3, layers, 2 * layers + 1 + i)
plt.plot(np.arange(time),
np.mean(np.abs(last_output_forget[i][:, 0, :]), axis=1))
plt.xticks(range(args.visualize_length), ticks)
plt.grid(True)
plt.title("forget_gate of layer " + str(i))
if args.local:
plt.show()
else:
plt.savefig(args.save_path + "/visualize_gates_" + str(num) +
".png")
logger.info("Figure \"visualize_gates_" + str(num) +
".png\" saved at directory: " + args.save_path)
