How to fix the error 'UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 36188: character maps to <undefined>'
How to fix the error 'UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 36188: character maps to <undefined>'
我正在训练 AI 使用 TensorFlow 1.14 和 python 2.6.7 写一本书。每当我 运行 我的训练 python 代码时，我都会收到错误消息 UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 36188: character maps to <undefined> 我已经重新安装了 TensorFlow 和 python 并搜索了论坛以尝试找到答案。回溯将我带到编码文件夹
中名为 cp1252.py 的文件
我运行宁的代码是
import numpy as np
import tensorflow as tf
import argparse
import time
import os
from six.moves import cPickle
from utils import TextLoader
from model import Model
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str, default='data/tinyshakespeare',
help='data directory containing input.txt')
parser.add_argument('--input_encoding', type=str, default=None,
help='character encoding of input.txt, from https://docs.python.org/3/library/codecs.html#standard-encodings')
parser.add_argument('--log_dir', type=str, default='logs',
help='directory containing tensorboard logs')
parser.add_argument('--save_dir', type=str, default='save',
help='directory to store checkpointed models')
parser.add_argument('--rnn_size', type=int, default=256,
help='size of RNN hidden state')
parser.add_argument('--num_layers', type=int, default=2,
help='number of layers in the RNN')
parser.add_argument('--model', type=str, default='lstm',
help='rnn, gru, or lstm')
parser.add_argument('--batch_size', type=int, default=50,
help='minibatch size')
parser.add_argument('--seq_length', type=int, default=25,
help='RNN sequence length')
parser.add_argument('--num_epochs', type=int, default=50,
help='number of epochs')
parser.add_argument('--save_every', type=int, default=1000,
help='save frequency')
parser.add_argument('--grad_clip', type=float, default=5.,
help='clip gradients at this value')
parser.add_argument('--learning_rate', type=float, default=0.002,
help='learning rate')
parser.add_argument('--decay_rate', type=float, default=0.97,
help='decay rate for rmsprop')
parser.add_argument('--gpu_mem', type=float, default=0.666,
help='%% of gpu memory to be allocated to this process. Default is 66.6%%')
parser.add_argument('--init_from', type=str, default=None,
help="""continue training from saved model at this path. Path must contain files saved by previous training process:
'config.pkl' : configuration;
'words_vocab.pkl' : vocabulary definitions;
'checkpoint' : paths to model file(s) (created by tf).
Note: this file contains absolute paths, be careful when moving files around;
'model.ckpt-*' : file(s) with model definition (created by tf)
""")
args = parser.parse_args()
train(args)
def train(args):
data_loader = TextLoader(args.data_dir, args.batch_size, args.seq_length, args.input_encoding)
args.vocab_size = data_loader.vocab_size
# check compatibility if training is continued from previously saved model
if args.init_from is not None:
# check if all necessary files exist
assert os.path.isdir(args.init_from)," %s must be a path" % args.init_from
assert os.path.isfile(os.path.join(args.init_from,"config.pkl")),"config.pkl file does not exist in path %s"%args.init_from
assert os.path.isfile(os.path.join(args.init_from,"words_vocab.pkl")),"words_vocab.pkl.pkl file does not exist in path %s" % args.init_from
ckpt = tf.train.get_checkpoint_state(args.init_from)
assert ckpt,"No checkpoint found"
assert ckpt.model_checkpoint_path,"No model path found in checkpoint"
# open old config and check if models are compatible
with open(os.path.join(args.init_from, 'config.pkl'), 'rb') as f:
saved_model_args = cPickle.load(f)
need_be_same=["model","rnn_size","num_layers","seq_length"]
for checkme in need_be_same:
assert vars(saved_model_args)[checkme]==vars(args)[checkme],"Command line argument and saved model disagree on '%s' "%checkme
# open saved vocab/dict and check if vocabs/dicts are compatible
with open(os.path.join(args.init_from, 'words_vocab.pkl'), 'rb') as f:
saved_words, saved_vocab = cPickle.load(f)
assert saved_words==data_loader.words, "Data and loaded model disagree on word set!"
assert saved_vocab==data_loader.vocab, "Data and loaded model disagree on dictionary mappings!"
with open(os.path.join(args.save_dir, 'config.pkl'), 'wb') as f:
cPickle.dump(args, f)
with open(os.path.join(args.save_dir, 'words_vocab.pkl'), 'wb') as f:
cPickle.dump((data_loader.words, data_loader.vocab), f)
model = Model(args)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(args.log_dir)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_mem)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
train_writer.add_graph(sess.graph)
tf.global_variables_initializer().run()
saver = tf.train.Saver(tf.global_variables())
# restore model
if args.init_from is not None:
saver.restore(sess, ckpt.model_checkpoint_path)
for e in range(model.epoch_pointer.eval(), args.num_epochs):
sess.run(tf.assign(model.lr, args.learning_rate * (args.decay_rate ** e)))
data_loader.reset_batch_pointer()
state = sess.run(model.initial_state)
speed = 0
if args.init_from is None:
assign_op = model.epoch_pointer.assign(e)
sess.run(assign_op)
if args.init_from is not None:
data_loader.pointer = model.batch_pointer.eval()
args.init_from = None
for b in range(data_loader.pointer, data_loader.num_batches):
start = time.time()
x, y = data_loader.next_batch()
feed = {model.input_data: x, model.targets: y, model.initial_state: state,
model.batch_time: speed}
summary, train_loss, state, _, _ = sess.run([merged, model.cost, model.final_state,
model.train_op, model.inc_batch_pointer_op], feed)
train_writer.add_summary(summary, e * data_loader.num_batches + b)
speed = time.time() - start
if (e * data_loader.num_batches + b) % args.batch_size == 0:
print("{}/{} (epoch {}), train_loss = {:.3f}, time/batch = {:.3f}" \
.format(e * data_loader.num_batches + b,
args.num_epochs * data_loader.num_batches,
e, train_loss, speed))
if (e * data_loader.num_batches + b) % args.save_every == 0 \
or (e==args.num_epochs-1 and b == data_loader.num_batches-1): # save for the last result
checkpoint_path = os.path.join(args.save_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step = e * data_loader.num_batches + b)
print("model saved to {}".format(checkpoint_path))
train_writer.close()
if __name__ == '__main__':
main()
如有任何帮助，我们将不胜感激
我可以提供任何需要的信息
编辑：我的回溯是
File "train.py", line 134, in <module>
main()
File "train.py", line 54, in main
train(args)
File "train.py", line 57, in train
data_loader = TextLoader(args.data_dir, args.batch_size, args.seq_length, args.input_encoding)
File "C:\Users\Josh\Desktop\word-rnn-tensorflow-master\utils.py", line 23, in __init__
self.preprocess(input_file, vocab_file, tensor_file, encoding)
File "C:\Users\Josh\Desktop\word-rnn-tensorflow-master\utils.py", line 66, in preprocess
data = f.read()
File "C:\Users\Josh\anaconda3\envs\tensorenviron\lib\encodings\cp1252.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 36188: character maps to <undefined>```
原来文本文件中有一个奇怪的字符。我所要做的就是用正确的符号替换所有奇怪的符号。感谢他的帮助！
我正在训练 AI 使用 TensorFlow 1.14 和 python 2.6.7 写一本书。每当我 运行 我的训练 python 代码时，我都会收到错误消息 UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 36188: character maps to <undefined> 我已经重新安装了 TensorFlow 和 python 并搜索了论坛以尝试找到答案。回溯将我带到编码文件夹
我运行宁的代码是
import numpy as np
import tensorflow as tf
import argparse
import time
import os
from six.moves import cPickle
from utils import TextLoader
from model import Model
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str, default='data/tinyshakespeare',
help='data directory containing input.txt')
parser.add_argument('--input_encoding', type=str, default=None,
help='character encoding of input.txt, from https://docs.python.org/3/library/codecs.html#standard-encodings')
parser.add_argument('--log_dir', type=str, default='logs',
help='directory containing tensorboard logs')
parser.add_argument('--save_dir', type=str, default='save',
help='directory to store checkpointed models')
parser.add_argument('--rnn_size', type=int, default=256,
help='size of RNN hidden state')
parser.add_argument('--num_layers', type=int, default=2,
help='number of layers in the RNN')
parser.add_argument('--model', type=str, default='lstm',
help='rnn, gru, or lstm')
parser.add_argument('--batch_size', type=int, default=50,
help='minibatch size')
parser.add_argument('--seq_length', type=int, default=25,
help='RNN sequence length')
parser.add_argument('--num_epochs', type=int, default=50,
help='number of epochs')
parser.add_argument('--save_every', type=int, default=1000,
help='save frequency')
parser.add_argument('--grad_clip', type=float, default=5.,
help='clip gradients at this value')
parser.add_argument('--learning_rate', type=float, default=0.002,
help='learning rate')
parser.add_argument('--decay_rate', type=float, default=0.97,
help='decay rate for rmsprop')
parser.add_argument('--gpu_mem', type=float, default=0.666,
help='%% of gpu memory to be allocated to this process. Default is 66.6%%')
parser.add_argument('--init_from', type=str, default=None,
help="""continue training from saved model at this path. Path must contain files saved by previous training process:
'config.pkl' : configuration;
'words_vocab.pkl' : vocabulary definitions;
'checkpoint' : paths to model file(s) (created by tf).
Note: this file contains absolute paths, be careful when moving files around;
'model.ckpt-*' : file(s) with model definition (created by tf)
""")
args = parser.parse_args()
train(args)
def train(args):
data_loader = TextLoader(args.data_dir, args.batch_size, args.seq_length, args.input_encoding)
args.vocab_size = data_loader.vocab_size
# check compatibility if training is continued from previously saved model
if args.init_from is not None:
# check if all necessary files exist
assert os.path.isdir(args.init_from)," %s must be a path" % args.init_from
assert os.path.isfile(os.path.join(args.init_from,"config.pkl")),"config.pkl file does not exist in path %s"%args.init_from
assert os.path.isfile(os.path.join(args.init_from,"words_vocab.pkl")),"words_vocab.pkl.pkl file does not exist in path %s" % args.init_from
ckpt = tf.train.get_checkpoint_state(args.init_from)
assert ckpt,"No checkpoint found"
assert ckpt.model_checkpoint_path,"No model path found in checkpoint"
# open old config and check if models are compatible
with open(os.path.join(args.init_from, 'config.pkl'), 'rb') as f:
saved_model_args = cPickle.load(f)
need_be_same=["model","rnn_size","num_layers","seq_length"]
for checkme in need_be_same:
assert vars(saved_model_args)[checkme]==vars(args)[checkme],"Command line argument and saved model disagree on '%s' "%checkme
# open saved vocab/dict and check if vocabs/dicts are compatible
with open(os.path.join(args.init_from, 'words_vocab.pkl'), 'rb') as f:
saved_words, saved_vocab = cPickle.load(f)
assert saved_words==data_loader.words, "Data and loaded model disagree on word set!"
assert saved_vocab==data_loader.vocab, "Data and loaded model disagree on dictionary mappings!"
with open(os.path.join(args.save_dir, 'config.pkl'), 'wb') as f:
cPickle.dump(args, f)
with open(os.path.join(args.save_dir, 'words_vocab.pkl'), 'wb') as f:
cPickle.dump((data_loader.words, data_loader.vocab), f)
model = Model(args)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(args.log_dir)
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=args.gpu_mem)
with tf.Session(config=tf.ConfigProto(gpu_options=gpu_options)) as sess:
train_writer.add_graph(sess.graph)
tf.global_variables_initializer().run()
saver = tf.train.Saver(tf.global_variables())
# restore model
if args.init_from is not None:
saver.restore(sess, ckpt.model_checkpoint_path)
for e in range(model.epoch_pointer.eval(), args.num_epochs):
sess.run(tf.assign(model.lr, args.learning_rate * (args.decay_rate ** e)))
data_loader.reset_batch_pointer()
state = sess.run(model.initial_state)
speed = 0
if args.init_from is None:
assign_op = model.epoch_pointer.assign(e)
sess.run(assign_op)
if args.init_from is not None:
data_loader.pointer = model.batch_pointer.eval()
args.init_from = None
for b in range(data_loader.pointer, data_loader.num_batches):
start = time.time()
x, y = data_loader.next_batch()
feed = {model.input_data: x, model.targets: y, model.initial_state: state,
model.batch_time: speed}
summary, train_loss, state, _, _ = sess.run([merged, model.cost, model.final_state,
model.train_op, model.inc_batch_pointer_op], feed)
train_writer.add_summary(summary, e * data_loader.num_batches + b)
speed = time.time() - start
if (e * data_loader.num_batches + b) % args.batch_size == 0:
print("{}/{} (epoch {}), train_loss = {:.3f}, time/batch = {:.3f}" \
.format(e * data_loader.num_batches + b,
args.num_epochs * data_loader.num_batches,
e, train_loss, speed))
if (e * data_loader.num_batches + b) % args.save_every == 0 \
or (e==args.num_epochs-1 and b == data_loader.num_batches-1): # save for the last result
checkpoint_path = os.path.join(args.save_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step = e * data_loader.num_batches + b)
print("model saved to {}".format(checkpoint_path))
train_writer.close()
if __name__ == '__main__':
main()
如有任何帮助，我们将不胜感激 我可以提供任何需要的信息 编辑：我的回溯是
File "train.py", line 134, in <module>
main()
File "train.py", line 54, in main
train(args)
File "train.py", line 57, in train
data_loader = TextLoader(args.data_dir, args.batch_size, args.seq_length, args.input_encoding)
File "C:\Users\Josh\Desktop\word-rnn-tensorflow-master\utils.py", line 23, in __init__
self.preprocess(input_file, vocab_file, tensor_file, encoding)
File "C:\Users\Josh\Desktop\word-rnn-tensorflow-master\utils.py", line 66, in preprocess
data = f.read()
File "C:\Users\Josh\anaconda3\envs\tensorenviron\lib\encodings\cp1252.py", line 23, in decode
return codecs.charmap_decode(input,self.errors,decoding_table)[0]
UnicodeDecodeError: 'charmap' codec can't decode byte 0x9d in position 36188: character maps to <undefined>```
原来文本文件中有一个奇怪的字符。我所要做的就是用正确的符号替换所有奇怪的符号。感谢他的帮助！