[英]Tensor Tensor("predictions/Softmax:0", shape=(?, 1000), dtype=float32) is not an element of this graph
I am trying to follow a simple tutorial on how to use a pre-trained VGG model for image classification.我正在尝试遵循有关如何使用预训练 VGG 模型进行图像分类的简单教程。 The code which I have:
我拥有的代码:
from keras.applications.vgg16 import VGG16
from keras.preprocessing.image import load_img, img_to_array
from keras.applications.vgg16 import preprocess_input, decode_predictions
import numpy as np
class KerasModel(object):
def __init__(self):
self.model = VGG16()
def evaluate(self):
image = load_img('mug.jpg', target_size=(224,224))
image = img_to_array(image)
image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
image = preprocess_input(image)
yhat = self.model.predict(image)
label = decode_predictions(yhat)
label = label[0][0]
return ('%s (%.2f%%)' % (label[1]), label[2]*100)
This gives the error: Tensor Tensor("predictions/Softmax:0", shape=(?, 1000), dtype=float32) is not an element of this graph.这给出了错误:Tensor Tensor("predictions/Softmax:0", shape=(?, 1000), dtype=float32) is not an element of this graph。
After some searching for this error I got to this code:在搜索了这个错误之后,我得到了这个代码:
from keras.applications.vgg16 import VGG16
from keras.preprocessing.image import load_img, img_to_array
from keras.applications.vgg16 import preprocess_input, decode_predictions
import numpy as np
import tensorflow as tf
graph = tf.get_default_graph()
class KerasModel(object):
def __init__(self):
self.model = VGG16()
def evaluate(self):
image = load_img('mug.jpg', target_size=(224,224))
image = img_to_array(image)
image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
image = preprocess_input(image)
with graph.as_default():
yhat = self.model.predict(image)
label = decode_predictions(yhat)
label = label[0][0]
return ('%s (%.2f%%)' % (label[1]), label[2]*100)
But this still results in the same error.但这仍然会导致相同的错误。 Could someone please help me out?
有人可以帮我吗? I don't understand what I am doing wrong because the tutorial seems to work for everyone.
我不明白我做错了什么,因为教程似乎对每个人都有效。
Model summary:型号概要:
_________________________________________________________________
xvision | Layer (type) Output Shape Param #
xvision | =================================================================
xvision | input_1 (InputLayer) (None, 224, 224, 3) 0
xvision | _________________________________________________________________
xvision | block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
xvision | _________________________________________________________________
xvision | block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
xvision | _________________________________________________________________
xvision | block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
xvision | _________________________________________________________________
xvision | block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
xvision | _________________________________________________________________
xvision | block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
xvision | _________________________________________________________________
xvision | block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
xvision | _________________________________________________________________
xvision | block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
xvision | _________________________________________________________________
xvision | block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
xvision | _________________________________________________________________
xvision | block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
xvision | _________________________________________________________________
xvision | block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
xvision | _________________________________________________________________
xvision | block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
xvision | _________________________________________________________________
xvision | block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
xvision | _________________________________________________________________
xvision | block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
xvision | _________________________________________________________________
xvision | block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
xvision | _________________________________________________________________
xvision | block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
xvision | _________________________________________________________________
xvision | block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
xvision | _________________________________________________________________
xvision | block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
xvision | _________________________________________________________________
xvision | block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
xvision | _________________________________________________________________
xvision | flatten (Flatten) (None, 25088) 0
xvision | _________________________________________________________________
xvision | fc1 (Dense) (None, 4096) 102764544
xvision | _________________________________________________________________
xvision | fc2 (Dense) (None, 4096) 16781312
xvision | _________________________________________________________________
xvision | predictions (Dense) (None, 1000) 4097000
xvision | =================================================================
xvision | Total params: 138,357,544
xvision | Trainable params: 138,357,544
xvision | Non-trainable params: 0
xvision | _________________________________________________________________
xvision | None
Seems that Keras is not thread safe so you need to initialize the model in each thread.似乎 Keras 不是线程安全的,因此您需要在每个线程中初始化模型。 A fix is calling: _make_predict_function()
修复调用:_make_predict_function()
It did work for me.它确实对我有用。 Here is a clean example:
这是一个干净的例子:
from keras.models import load_model
def load_model():
model = load_model('./my_model.h5')
model._make_predict_function()
print('model loaded') # just to keep track in your server
return model
Hope this helps.希望这可以帮助。
As your code is fine, running with a clean environment should solve it.由于您的代码很好,在干净的环境中运行应该可以解决它。
Clear keras cache at ~/.keras/
清除
~/.keras/
keras 缓存
Run on a new environment, with the right packages (can be done easily with anaconda)使用正确的包在新环境中运行(使用 anaconda 可以轻松完成)
Make sure you are on a fresh session, keras.backend.clear_session()
should remove all existing tf graphs.确保您处于新会话中,
keras.backend.clear_session()
应删除所有现有的 tf 图。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.