Tensorflow:尽管数据中没有字符串，但使用 tflearn 时不支持将字符串转换为浮点数错误 [英] Tensorflow: Cast string to float is not supported error when using tflearn despite having no strings in data

问题描述

我似乎无法在我的代码中找到我的错误，其中有任何字符串被错误地转换为浮点数.但它给了我这个错误:

I can't seem to find my error in my code where there is any string that is wrongly converted to a float. But yet it gives me this error:

W tensorflow/core/framework/op_kernel.cc:958] Unimplemented: Cast string to float is not supported
E tensorflow/core/common_runtime/executor.cc:334] Executor failed to create kernel. Unimplemented: Cast string to float is not supported
     [[Node: Adam/apply_grad_op_0/update_FullyConnected_1/b/Cast_2 = Cast[DstT=DT_FLOAT, SrcT=DT_STRING, _class=["loc:@FullyConnected_1/b"], _device="/job:localhost/replica:0/task:0/cpu:0"](Adam/apply_grad_op_0/learning_rate)]]
W tensorflow/core/framework/op_kernel.cc:958] Unimplemented: Cast string to float is not supported
E tensorflow/core/common_runtime/executor.cc:334] Executor failed to create kernel. Unimplemented: Cast string to float is not supported
     [[Node: Adam/apply_grad_op_0/update_Conv2D/W/Cast_2 = Cast[DstT=DT_FLOAT, SrcT=DT_STRING, _class=["loc:@Conv2D/W"], _device="/job:localhost/replica:0/task:0/cpu:0"](Adam/apply_grad_op_0/learning_rate)]]
--
Traceback (most recent call last):
  File "code.py", line 63, in <module>
    snapshot_step = 100, show_metric = True, run_id = 'convnet_images')
  File "/usr/local/lib/python2.7/dist-packages/tflearn/models/dnn.py", line 214, in fit
    callbacks=callbacks)
  File "/usr/local/lib/python2.7/dist-packages/tflearn/helpers/trainer.py", line 304, in fit
    show_metric)
  File "/usr/local/lib/python2.7/dist-packages/tflearn/helpers/trainer.py", line 759, in _train
    feed_batch)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 717, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 915, in _run
    feed_dict_string, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 965, in _do_run
    target_list, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 985, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors.UnimplementedError: Cast string to float is not supported
     [[Node: Adam/apply_grad_op_0/update_Conv2D/W/Cast_2 = Cast[DstT=DT_FLOAT, SrcT=DT_STRING, _class=["loc:@Conv2D/W"], _device="/job:localhost/replica:0/task:0/cpu:0"](Adam/apply_grad_op_0/learning_rate)]]

Caused by op u'Adam/apply_grad_op_0/update_Conv2D/W/Cast_2', defined at:
  File "code.py", line 59, in <module>
    model = tflearn.DNN(network, tensorboard_verbose = 3)
  File "/usr/local/lib/python2.7/dist-packages/tflearn/models/dnn.py", line 63, in __init__
    best_val_accuracy=best_val_accuracy)
  File "/usr/local/lib/python2.7/dist-packages/tflearn/helpers/trainer.py", line 119, in __init__
    clip_gradients)
  File "/usr/local/lib/python2.7/dist-packages/tflearn/helpers/trainer.py", line 649, in initialize_training_ops
    name="apply_grad_op_" + str(i))
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 322, in apply_gradients
    update_ops.append(self._apply_dense(grad, var))
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/adam.py", line 135, in _apply_dense
    math_ops.cast(self._lr_t, var.dtype.base_dtype),
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 616, in cast
    return gen_math_ops.cast(x, base_type, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 419, in cast
    result = _op_def_lib.apply_op("Cast", x=x, DstT=DstT, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 749, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2380, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1298, in __init__
    self._traceback = _extract_stack()

UnimplementedError (see above for traceback): Cast string to float is not supported
     [[Node: Adam/apply_grad_op_0/update_Conv2D/W/Cast_2 = Cast[DstT=DT_FLOAT, SrcT=DT_STRING, _class=["loc:@Conv2D/W"], _device="/job:localhost/replica:0/task:0/cpu:0"](Adam/apply_grad_op_0/learning_rate)]]

我已经检查了图像像素的数值，并确保它们不是字符串.代码中错误转换的字符串在哪里?

I have checked down to the numeric values of the pixels of my images and ensured they are not strings. Where is the string wrongly converted in the code?

我的代码是这样的:

import tensorflow as tf
import tflearn
from scipy.misc import imread, imresize
import numpy as np
np.set_printoptions(threshold=np.nan)

image = imread('image.jpg')
image2 = imread('image2.jpg')

image3 = imread('image3.jpg')
image4 = imread('image4.jpg')

image = np.resize(image, (256, 256, 1))
image2 = np.resize(image2, (256, 256, 1))
image3 = np.resize(image3, (256, 256, 1))
image4 = np.resize(image4, (256, 256, 1 ))   

image_train = np.stack((image, image2), axis = 0) / 255.0
image_test = np.stack((image3, image4), axis = 0) / 255.0

Y = np.zeros((2,1), dtype = np.float64)

# build the neural net
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression

network = input_data(shape = [None, 256, 256, 1], name = 'input')
network = conv_2d(network, 32, 3, activation = 'relu', regularizer = 'L2')
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation = 'relu', regularizer = 'L2')
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation = 'tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 1, activation = 'softmax')
network = regression(network, optimizer = 'adam', learning_rate = '0.001', name = 'target')

#Training
model = tflearn.DNN(network, tensorboard_verbose = 3)
print type(model)
model.fit({'input': image_train}, {'target': Y}, n_epoch = 20, batch_size = 1,
          validation_set = ({'input': image_test}, {'target': Y}),
          snapshot_step = 100, show_metric = True, run_id = 'convnet_images')

推荐答案

我也遇到了同样的问题，你写:

I had the same problem, you write:

learning_rate = '0.001'

但是 learning_rate 是一个 float 而不是 string 所以只需写:

But the learning_rate is a float not a string so just write:

learning_rate = 0.001

这篇关于Tensorflow:尽管数据中没有字符串，但使用 tflearn 时不支持将字符串转换为浮点数错误的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！