Python 基于张量流的CNN预测

我对python和tensorflow很陌生，但已经用我自己保存为tf.records的图像数据库构建、训练和验证了一个CNN。 现在我想让模型在一张图片中读取并实时预测。因此，我想通过去掉解析器（对保存为tf.records的图像进行解码）来修改我的验证脚本，并且不批处理输入图像，因为我只想预测一个。不知何故，我总是出现以下错误：

TypeError: Value passed to parameter 'input' has DataType uint8 not in list of allowed values: float16, bfloat16, float32, float64

我仔细查看了用于创建tf.records的脚本，并将它们与用于培训和验证的脚本中使用的解析器进行了比较，但没有发现错误

如果你能帮我找到错误，或者给我一个更简单的方法，让我用一个已经受过训练的CNN来预测课程，我将不胜感激

import tensorflow as tf
import cv2

num_classes = 2
crop_top = 5
crop_bottom = 10
crop_sides = 5
img_size_height = 80
img_size_width = 100
model_dir = "./2cv_128fc"


def load_image():
    img = cv2.imread('./dir_pred_img/img_2.jpg')
    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    img = cv2.resize(img, (img_size_width + (2 * crop_sides), img_size_height + crop_top + crop_bottom),
                     interpolation=cv2.INTER_CUBIC)
    img = img[crop_top:(img_size_height + crop_top), crop_sides:(img_size_width + crop_sides)]
    features = {'image': img}
    return features


def conv_nn(input_layer):
    conv_1 = tf.layers.conv2d(inputs=input_layer, name='conv_layer_1', filters=32, kernel_size=3, padding='same',
                              activation=tf.nn.relu)

    pool_1 = tf.layers.max_pooling2d(inputs=conv_1, pool_size=2, strides=2)
    conv_2 = tf.layers.conv2d(inputs=pool_1, name='conv_layer_2', filters=32, kernel_size=3, padding='same',
                              activation=tf.nn.relu)

    pool_2 = tf.layers.max_pooling2d(inputs=conv_2, pool_size=2, strides=2)
    flatten = tf.contrib.layers.flatten(pool_2)
    fc_layer = tf.layers.dense(inputs=flatten, name='fully_connected_layer', units=128, activation=tf.nn.relu)
    fc_layer = tf.layers.dropout(fc_layer, rate=0.5, noise_shape=None, seed=None)
    output_layer = tf.layers.dense(inputs=fc_layer, name='output_layer', units=num_classes)
    return output_layer


def model_fn(features):
    input_layer = features["image"]
    input_layer = tf.identity(input_layer, name="input_tensor")
    input_layer = tf.reshape(input_layer, [-1, img_size_height, img_size_width, 1])  # 1.tensor 2.shape
    input_layer = tf.identity(input_layer, name="input_tensor_reshaped")

    logits = conv_nn(input_layer)

    pred = tf.nn.softmax(logits=logits)
    return pred


model = tf.estimator.Estimator(model_fn=model_fn, model_dir=model_dir)
prediction = list(model.predict(input_fn=load_image))
print(prediction[0])

完整错误消息：

WARNING:tensorflow:Input graph does not use tf.data.Dataset or contain a QueueRunner. That means predict yields forever. This is probably a mistake.
Traceback (most recent call last):
  File "C:/Users/Dell/PycharmProjects/create_data/pred_img.py", line 54, in <module>
    prediction = list(model.predict(input_fn=load_image))
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\estimator\estimator.py", line 577, in predict
    features, None, model_fn_lib.ModeKeys.PREDICT, self.config)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\estimator\estimator.py", line 1195, in _call_model_fn
    model_fn_results = self._model_fn(features=features, **kwargs)
  File "C:/Users/Dell/PycharmProjects/create_data/pred_img.py", line 47, in model_fn
    logits = conv_nn(input_layer)
  File "C:/Users/Dell/PycharmProjects/create_data/pred_img.py", line 27, in conv_nn
    activation=tf.nn.relu)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\layers\convolutional.py", line 417, in conv2d
    return layer.apply(inputs)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 817, in apply
    return self.__call__(inputs, *args, **kwargs)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\layers\base.py", line 374, in __call__
    outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 757, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\keras\layers\convolutional.py", line 194, in call
    outputs = self._convolution_op(inputs, self.kernel)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 868, in __call__
    return self.conv_op(inp, filter)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 520, in __call__
    return self.call(inp, filter)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 204, in __call__
    name=self.name)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 1043, in conv2d
    data_format=data_format, dilations=dilations, name=name)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 609, in _apply_op_helper
    param_name=input_name)
  File "C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 60, in _SatisfiesTypeConstraint
    ", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: Value passed to parameter 'input' has DataType uint8 not in list of allowed values: float16, bfloat16, float32, float64

警告：tensorflow:输入图形未使用tf.data.Dataset或包含QueueRunner。这意味着永远预测收益率。这可能是个错误。
回溯（最近一次呼叫最后一次）：
文件“C:/Users/Dell/PycharmProjects/create_data/pred_img.py”，第54行，在
预测=列表（model.predict（输入\加载\图像））
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\estimator\estimator.py”，第577行，在predict中
功能，无，模型\u fn\u lib.ModeKeys.PREDICT，self.config）
文件“C:\Users\Dell\AppData\Local\Programs\Python\Python36\lib\site packages\tensorflow\Python\estimator\estimator.py”，第1195行，位于调用模型fn中
模型\结果=自身。\模型\结果（特征=特征，**kwargs）
文件“C:/Users/Dell/PycharmProjects/create_data/pred_img.py”，第47行，型号fn
logits=conv\u nn（输入层）
conv_nn中的文件“C:/Users/Dell/PycharmProjects/create_data/pred_img.py”，第27行
激活=tf.nn.relu）
conv2d中的文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\layers\convolutional.py”，第417行
返回层。应用（输入）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\keras\engine\base\u layer.py”，第817行，应用
返回自我。调用（输入，*args，**kwargs）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\layers\base.py”，第374行，在调用中__
输出=超级（层，自身）。\调用（输入，*args，**kwargs）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\keras\engine\base\u layer.py”，第757行，在调用中__
输出=自调用（输入，*args，**kwargs）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\keras\layers\convolutional.py”，第194行，在调用中
输出=self.\u卷积\u op（输入，self.kernel）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\ops\nn\u ops.py”，第868行，在调用中__
返回自转换操作（inp，过滤器）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\ops\nn\u ops.py”，第520行，在调用中__
返回自调用（inp、筛选器）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\ops\nn\u ops.py”，第204行，在调用中__
name=self.name）
conv2d中的文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\ops\gen\u nn\u ops.py”，第1043行
数据\格式=数据\格式，膨胀=膨胀，名称=名称）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\framework\op\u def\u library.py”，第609行，位于应用\u op\u帮助程序中
参数名称=输入名称）
文件“C:\Users\Dell\AppData\Local\Programs\Python\36\lib\site packages\tensorflow\Python\framework\op_def_library.py”，第60行，在满足类型约束中
“，”.join（数据类型.as_数据类型（x）.x在允许的_列表中的名称）））
TypeError:传递给参数“input”的值的数据类型uint8不在允许值列表中：float16、bfloat16、float32、float64

以下代码描述了如何使用keras实现这一点

import keras
from keras.layers import Input, Convolution2D, MaxPooling2D, Cropping2D, Dense, Flatten, Dropout
from keras.preprocessing import image
from keras.models import Model
from keras.optimizers import Adam
import cv2
import numpy as np

# parameters
num_classes = 2
crop_top = 5
crop_bottom = 10
crop_sides = 5
img_size_height = 80
img_size_width = 100
channels = 3
input_shape = (img_size_height, img_size_width, channels)
activation = 'relu'
learning_rate = 0.0001

if num_classes == 2:
    loss = 'binary_crossentropy'
else:
    loss = 'categorical_crossentropy'


test_image = image.load_img('./data/img.png')
test_image = image.img_to_array(test_image)
input_shape = test_image.shape

def model(input_shape=input_shape):

    inputs = Input(shape=input_shape)

   # cropping=((pixels_from_top, pixels_from_bottom), (pixels_from_left, pixels_from_right))
    cropping = Cropping2D(cropping=((crop_top, crop_bottom), (crop_sides, crop_sides)))(inputs)
    conv_1 = Convolution2D(32, kernel_size=(3, 3), padding='same', activation=activation)(cropping)
    pool_1 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(conv_1)
    conv_2 = Convolution2D(32, kernel_size=(3, 3), padding='same', activation=activation)(pool_1)
    pool_2 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(conv_2)

    flatten = Flatten()(pool_2)
    dense_1 = Dense(128, activation=activation, name='fully_connected_layer')(flatten)
    dropout = Dropout(0.5)(dense_1)

    outputs = Dense(num_classes, activation='softmax')(dropout)

    model = Model(inputs=inputs, outputs=outputs)

    adam = Adam(lr=learning_rate)
    model.compile(optimizer=adam, loss=loss, metrics=['acc', 'mse', 'mae'])
    model.summary()

    return model

test_image = np.expand_dims(test_image, axis=0)
model = model(input_shape)
# note that without training we will only get random results
prediction = model.predict_on_batch(test_image)
print(prediction)

我找到了解决办法。 我在def load_image（）的末尾添加了以下行，并返回了数据集而不是feautures

dataset = tf.data.Dataset.from_tensors(features)
return dataset

---

谢谢你的回答。但是因为我已经训练了我的CNN，我必须使用Tensorflow，Keras不是我的选择。我将尝试理解Keras模型，并希望这将帮助我使tensorflow模型工作。model.predict\u on\u batch（）命令可能会有所帮助。