我正在尝试将许多csv文件加载到单个TFRecord文件中,然后能够将TFRecord提供给我的模型。我下面是我的所有代码,我试图将其分解为我认为我在做什么。
生成数据..目标变量将是最后一列。
for i in range(10):
filename = './Data/random_csv' + str(i) + '.csv'
pd.DataFrame(np.random.randint(0,100,size=(100, 50))).to_csv(filename)
制作TFRecord档案的功能
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _float_feature(value):
return tf.train.Feature(float_list=tf.train.FloatList(value=[value]))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def make_q_list(filepathlist, filetype):
filepathlist = filepathlist
filepaths = []
labels = []
for path in filepathlist:
data_files = os.listdir(path)
for data in data_files:
if data.endswith(filetype):
data_file = os.path.join(path, data)
data_file = data_file
data_label = os.path.basename(os.path.normpath(path))
filepaths.append(data_file)
labels.append(data_label)
return filepaths, labels
def rnn_list_format(df):
input_data_list = []
output_data_list = []
y = df[df.columns[-1]]
X = df[df.columns[:-1]]
for i in range(len(df)):
output_data_list.append(y.loc[i])
input_data_list.append(X.loc[i].as_matrix())
return input_data_list, output_data_list
def data_split(df):
y = df[df.columns[-1]]
X = df[df.columns[:-1]]
X, y = X.as_matrix(), y.as_matrix()
return X, y
将csvs加载到Pandas中的功能。然后取最后一列,使其成为我的目标变量y。 Pandas数据帧将转换为numpy数组并写入TFRecords文件。
def tables_to_TF(queue_list, tf_filename, file_type='csv'):
#Target variable needs to be the last column of data
filepath = os.path.join(tf_filename)
print('Writing', filepath)
writer = tf.python_io.TFRecordWriter(tf_filename)
for file in tqdm(queue_list):
if file_type == 'csv':
data = pd.read_csv(file)
X, y = data_split(data)
elif file_type == 'hdf':
data = pd.read_hdf(file)
X, y = data_split(data)
else:
print(file_type, 'is not supported at this time...')
break
rec_count = X.shape[0]
for index in range(rec_count):
_X = np.asarray(X[index]).tostring()
_y = np.asarray(y[index]).tostring()
example = tf.train.Example(features=tf.train.Features(feature={
'X': _bytes_feature(_X),
'y': _bytes_feature(_y)}))
writer.write(example.SerializeToString())
读取TFRecords文件的功能。
def read_and_decode(filename_queue, datashape=160*160*3):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
features={
'X': tf.FixedLenFeature([], tf.string),
'y': tf.FixedLenFeature([], tf.string)
})
X = tf.decode_raw(features['X'], tf.float32)
X.set_shape([datashape])
X = tf.cast(X, tf.float32)
y = tf.decode_raw(features['y'], tf.float32)
y.set_shape([1])
y = tf.cast(y, tf.float32)
return X, y
在Tensorflow中创建批次
def inputs(train_dir, file, batch_size, num_epochs, n_classes, one_hot_labels=False, datashape=160*160*3):
if not num_epochs: num_epochs = None
filename = os.path.join(train_dir, file)
with tf.name_scope('input'):
filename_queue = tf.train.string_input_producer(
[filename], num_epochs=num_epochs)
X, y = read_and_decode(filename_queue, datashape)
if one_hot_labels:
label = tf.one_hot(label, n_classes, dtype=tf.int32)
example_batch, label_batch = tf.train.shuffle_batch(
[X, y], batch_size=batch_size, num_threads=2,
capacity=2000, enqueue_many=False,
# Ensures a minimum amount of shuffling of examples.
min_after_dequeue=1000, name=file)
return example_batch, label_batch
根据创建的数据制作TFRecord文件。
filepathlist = ['./Data']
q, _ = make_q_list(filepathlist, '.csv')
tffilename = 'Demo_TFR.tfrecords'
tables_to_TF(q, tffilename, file_type='csv')
尝试将TFRecord文件加载到queueRunner中。
X_train_batch, y_train_batch = inputs('./',
'Demo_TFR.tfrecords',
50,
1,
0,
one_hot_labels=False,
datashape=50)
sess = tf.Session()
init_op = tf.group(tf.global_variables_initializer())
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
sess.run([X_train_batch, y_train_batch])
错误
INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.FailedPreconditionError'>, Attempting to use uninitialized value input/input_producer/limit_epochs/epochs
[[Node: input/input_producer/limit_epochs/CountUpTo = CountUpTo[T=DT_INT64, _class=["loc:@input/input_producer/limit_epochs/epochs"], limit=1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/input_producer/limit_epochs/epochs)]]
Caused by op 'input/input_producer/limit_epochs/CountUpTo', defined at:
File "/home/mcamp/anaconda3/lib/python3.5/runpy.py", line 184, in _run_module_as_main
"__main__", mod_spec)
File "/home/mcamp/anaconda3/lib/python3.5/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/__main__.py", line 3, in <module>
app.launch_new_instance()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelapp.py", line 474, in start
ioloop.IOLoop.instance().start()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tornado/ioloop.py", line 887, in start
handler_func(fd_obj, events)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 390, in execute_request
user_expressions, allow_stdin)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/zmqshell.py", line 501, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2821, in run_ast_nodes
if self.run_code(code, result):
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-13-a00f528d3e80>", line 7, in <module>
datashape=50)
File "<ipython-input-11-468d0a66f589>", line 94, in inputs
[filename], num_epochs=num_epochs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/input.py", line 230, in string_input_producer
cancel_op=cancel_op)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/input.py", line 156, in input_producer
input_tensor = limit_epochs(input_tensor, num_epochs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/input.py", line 96, in limit_epochs
counter = epochs.count_up_to(num_epochs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/variables.py", line 652, in count_up_to
return state_ops.count_up_to(self._variable, limit=limit)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/gen_state_ops.py", line 126, in count_up_to
result = _op_def_lib.apply_op("CountUpTo", ref=ref, limit=limit, name=name)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
self._traceback = _extract_stack()
FailedPreconditionError (see above for traceback): Attempting to use uninitialized value input/input_producer/limit_epochs/epochs
[[Node: input/input_producer/limit_epochs/CountUpTo = CountUpTo[T=DT_INT64, _class=["loc:@input/input_producer/limit_epochs/epochs"], limit=1, _device="/job:localhost/replica:0/task:0/cpu:0"](input/input_producer/limit_epochs/epochs)]]
---------------------------------------------------------------------------
OutOfRangeError Traceback (most recent call last)
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1020 try:
-> 1021 return fn(*args)
1022 except errors.OpError as e:
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
1002 feed_dict, fetch_list, target_list,
-> 1003 status, run_metadata)
1004
/home/mcamp/anaconda3/lib/python3.5/contextlib.py in __exit__(self, type, value, traceback)
65 try:
---> 66 next(self.gen)
67 except StopIteration:
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
468 compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 469 pywrap_tensorflow.TF_GetCode(status))
470 finally:
OutOfRangeError: RandomShuffleQueue '_7_input_1/Demo_TFR.tfrecords/random_shuffle_queue' is closed and has insufficient elements (requested 50, current size 0)
[[Node: input_1/Demo_TFR.tfrecords = QueueDequeueMany[_class=["loc:@input_1/Demo_TFR.tfrecords/random_shuffle_queue"], component_types=[DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input_1/Demo_TFR.tfrecords/random_shuffle_queue, input_1/Demo_TFR.tfrecords/n)]]
During handling of the above exception, another exception occurred:
OutOfRangeError Traceback (most recent call last)
<ipython-input-17-a00f528d3e80> in <module>()
12 coord = tf.train.Coordinator()
13 threads = tf.train.start_queue_runners(sess=sess, coord=coord)
---> 14 sess.run([X_train_batch, y_train_batch])
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
764 try:
765 result = self._run(None, fetches, feed_dict, options_ptr,
--> 766 run_metadata_ptr)
767 if run_metadata:
768 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
962 if final_fetches or final_targets:
963 results = self._do_run(handle, final_targets, final_fetches,
--> 964 feed_dict_string, options, run_metadata)
965 else:
966 results = []
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1012 if handle is None:
1013 return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1014 target_list, options, run_metadata)
1015 else:
1016 return self._do_call(_prun_fn, self._session, handle, feed_dict,
/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1032 except KeyError:
1033 pass
-> 1034 raise type(e)(node_def, op, message)
1035
1036 def _extend_graph(self):
OutOfRangeError: RandomShuffleQueue '_7_input_1/Demo_TFR.tfrecords/random_shuffle_queue' is closed and has insufficient elements (requested 50, current size 0)
[[Node: input_1/Demo_TFR.tfrecords = QueueDequeueMany[_class=["loc:@input_1/Demo_TFR.tfrecords/random_shuffle_queue"], component_types=[DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input_1/Demo_TFR.tfrecords/random_shuffle_queue, input_1/Demo_TFR.tfrecords/n)]]
Caused by op 'input_1/Demo_TFR.tfrecords', defined at:
File "/home/mcamp/anaconda3/lib/python3.5/runpy.py", line 184, in _run_module_as_main
"__main__", mod_spec)
File "/home/mcamp/anaconda3/lib/python3.5/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/__main__.py", line 3, in <module>
app.launch_new_instance()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelapp.py", line 474, in start
ioloop.IOLoop.instance().start()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tornado/ioloop.py", line 887, in start
handler_func(fd_obj, events)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tornado/stack_context.py", line 275, in null_wrapper
return fn(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 276, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 228, in dispatch_shell
handler(stream, idents, msg)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/kernelbase.py", line 390, in execute_request
user_expressions, allow_stdin)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/ipykernel/zmqshell.py", line 501, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2717, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2821, in run_ast_nodes
if self.run_code(code, result):
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/IPython/core/interactiveshell.py", line 2881, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-17-a00f528d3e80>", line 7, in <module>
datashape=50)
File "<ipython-input-15-468d0a66f589>", line 105, in inputs
min_after_dequeue=1000, name=file)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/training/input.py", line 917, in shuffle_batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/data_flow_ops.py", line 458, in dequeue_many
self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 1099, in _queue_dequeue_many
timeout_ms=timeout_ms, name=name)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/mcamp/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1128, in __init__
self._traceback = _extract_stack()
OutOfRangeError (see above for traceback): RandomShuffleQueue '_7_input_1/Demo_TFR.tfrecords/random_shuffle_queue' is closed and has insufficient elements (requested 50, current size 0)
[[Node: input_1/Demo_TFR.tfrecords = QueueDequeueMany[_class=["loc:@input_1/Demo_TFR.tfrecords/random_shuffle_queue"], component_types=[DT_FLOAT, DT_FLOAT], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](input_1/Demo_TFR.tfrecords/random_shuffle_queue, input_1/Demo_TFR.tfrecords/n)]]
修改 以下代码似乎是问题的根本原因。我想我没有正确解析TFRecord文件(duh *)。我想也许我不是在读正确的数据类型。几乎完全相同的代码将图片读入TFRecord并退出..唯一的区别是我试图通过它发送float32值。
def read_and_decode(filename_queue, datashape=160*160*3):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
features={
'X': tf.FixedLenFeature([], tf.string),
'y': tf.FixedLenFeature([], tf.string)
})
X = tf.decode_raw(features['X'], tf.float32)
X.set_shape([datashape])
X = tf.cast(X, tf.float32)
y = tf.decode_raw(features['y'], tf.float32)
y.set_shape([1])
y = tf.cast(y, tf.float32)
return X, y
答案 0 :(得分:0)
有很多东西要关注,所以我不确定,但最快的检查是你的“num_epochs”设置是否正确。达到纪元限制时会抛出那些OutOfRangeErrors。