I am working on a character level Recurrent Neural Network. To train the net I copied a text corpus from the internet. Here is the chunk of code that has the error in it :
X = np.zeros((int(len(data)/SEQ_LENGTH), SEQ_LENGTH, VOCAB_SIZE))
y = np.zeros((int(len(data)/SEQ_LENGTH), SEQ_LENGTH, VOCAB_SIZE))
for i in range(0, int(len(data)/SEQ_LENGTH)):
X_sequence = data[i*SEQ_LENGTH:(i+1)*SEQ_LENGTH]
X_sequence_ix = [char_to_ix[value] for value in X_sequence]
input_sequence = np.zeros((SEQ_LENGTH, VOCAB_SIZE))
for j in range(SEQ_LENGTH):
input_sequence[j][X_sequence_ix[j]] = 1.
X[i] = input_sequence
y_sequence = data[i*SEQ_LENGTH+1:(i+1)*SEQ_LENGTH+1]
y_sequence_ix = [char_to_ix[value] for value in y_sequence]
target_sequence = np.zeros((SEQ_LENGTH, VOCAB_SIZE))
for j in range(SEQ_LENGTH):
target_sequence[j][y_sequence_ix[j]] = 1
y[i] = target_sequence
Basically all I am doing is converting characters to their ASCII equivalent. y_sequence
is the character sequence and y_sequence_ix
is its corresponding ASCII sequence. VOCAB_SIZE
variable contains the number of unique character in the text corpus. The error occurs in this line :
target_sequence[j][y_sequence_ix[j]] = 1
Complete source code along with text corpus : https://github.com/tanmay-edgelord/charRNN
Please ask for any information that is required in order for you to answer the question.
EDIT
TRACEBACK upon calling function traceback.print_stack()
File "/usr/lib/python3.5/runpy.py", line 184, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.5/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.5/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python3.5/dist-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelapp.py", line 478, in start
self.io_loop.start()
File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/usr/local/lib/python3.5/dist-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python3.5/dist-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python3.5/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python3.5/dist-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.5/dist-packages/ipykernel/zmqshell.py", line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py", line 2728, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py", line 2856, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python3.5/dist-packages/IPython/core/interactiveshell.py", line 2910, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-15-b47f6c9a5577>", line 2, in <module>
traceback.print_stack()
The issue is in y_sequence_ix[j]
because your j
range function is using SEQ_LENGTH+1. This is what you want since you're predicting the next
value in the list but it also creates an issue in that y_sequence_ix
is 1 sample too short on the last iteration of i
when data
splits evenly with SEQ_LENGTH
.
import string
import random
import numpy as np
ix_to_char = list(string.ascii_lowercase)
data = [random.choice(string.ascii_lowercase) for x in range(1000)]
char_to_ix = {v:i for i,v in enumerate(ix_to_char)}
VOCAB_SIZE = len(char_to_ix)
SEQ_LENGTH = 5
usable_len = len(data)-1 #Note: don't try to use the last entry in data
X = np.zeros((int(usable_len/SEQ_LENGTH), SEQ_LENGTH, VOCAB_SIZE))
y = np.zeros((int(usable_len/SEQ_LENGTH), SEQ_LENGTH, VOCAB_SIZE))
for i in range(0, int(usable_len/SEQ_LENGTH)):
X_sequence = data[i*SEQ_LENGTH:(i+1)*SEQ_LENGTH]
X_sequence_ix = [char_to_ix[value] for value in X_sequence]
input_sequence = np.zeros((SEQ_LENGTH, VOCAB_SIZE))
for j in range(SEQ_LENGTH):
input_sequence[j][X_sequence_ix[j]] = 1.
X[i] = input_sequence
y_sequence = data[i*SEQ_LENGTH+1:(i+1)*SEQ_LENGTH+1]
y_sequence_ix = [char_to_ix[value] for value in y_sequence]
target_sequence = np.zeros((SEQ_LENGTH, VOCAB_SIZE))
for j in range(SEQ_LENGTH):
target_sequence[j][y_sequence_ix[j]] = 1
y[i] = target_sequence
Other that the data creation at the top, the only thing modified here is use len(data)-1
in the data creation instead of len(data)
. By truncating a single value, you assure you won't get an index out of range
type error. This is the easiest thing to do, however you could also set SEQ_LENGTH to be a value that isn't an even multiple of len(data), ie.. 6
would work for the above example.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.