keras错误预测

Question

我正在尝试使用keras神经网络识别绘制数字的画布图像并输出数字.我保存了神经网络并使用django来运行Web界面.但每当我运行它时,我会收到内部服务器错误和服务器端代码错误.错误说明异常:检查时出错:预期dense_input_1具有形状(无,784)但是具有形状的数组(784,1).我唯一的主要观点是

from django.shortcuts import render
from django.http import HttpResponse
import StringIO
from PIL import Image
import numpy as np
import re
from keras.models import model_from_json
def home(request):
    if request.method=="POST":
        vari=request.POST.get("imgBase64","")
        imgstr=re.search(r'base64,(.*)', vari).group(1)
        tempimg = StringIO.StringIO(imgstr.decode('base64'))
        im=Image.open(tempimg).convert("L")
        im.thumbnail((28,28), Image.ANTIALIAS)
        img_np= np.asarray(im)
        img_np=img_np.flatten()
        img_np.astype("float32")
        img_np=img_np/255
        json_file = open('model.json', 'r')
        loaded_model_json = json_file.read()
        json_file.close()
        loaded_model = model_from_json(loaded_model_json)
        # load weights into new model
        loaded_model.load_weights("model.h5")
        # evaluate loaded model on test data
        loaded_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
        output=loaded_model.predict(img_np)
        score=output.tolist()
        return HttpResponse(score)
    else:
        return render(request, "digit/index.html")

我检查过的链接是:

• 这里
• 这里
• 和这里

编辑 遵守Rohan的建议,这是我的堆栈跟踪

Internal Server Error: /home/
Traceback (most recent call last):
  File "/usr/local/lib/python2.7/dist-packages/django/core/handlers/base.py", line 149, in get_response
    response = self.process_exception_by_middleware(e, request)
  File "/usr/local/lib/python2.7/dist-packages/django/core/handlers/base.py", line 147, in get_response
    response = wrapped_callback(request, *callback_args, **callback_kwargs)
  File "/home/vivek/keras/neural/digit/views.py", line 27, in home
output=loaded_model.predict(img_np)
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 671, in predict
return self.model.predict(x, batch_size=batch_size, verbose=verbose)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1161, in predict
check_batch_dim=False)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 108, in standardize_input_data
str(array.shape))
Exception: Error when checking : expected dense_input_1 to have shape (None, 784) but got array with shape (784, 1)

另外,我有我最初训练网络的模型.

import numpy
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.utils import np_utils
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
(X_train, y_train), (X_test, y_test) = mnist.load_data()
for item in y_train.shape:
    print item
num_pixels = X_train.shape[1] * X_train.shape[2]
X_train = X_train.reshape(X_train.shape[0], num_pixels).astype('float32')
X_test = X_test.reshape(X_test.shape[0], num_pixels).astype('float32')
# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
print X_train.shape
# one hot encode outputs
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]
# define baseline model
def baseline_model():
    # create model
    model = Sequential()
    model.add(Dense(num_pixels, input_dim=num_pixels, init='normal', activation='relu'))
    model.add(Dense(num_classes, init='normal', activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model
# build the model
model = baseline_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), nb_epoch=20, batch_size=200, verbose=1)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Baseline Error: %.2f%%" % (100-scores[1]*100))
# serialize model to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("model.h5")
print("Saved model to disk")

编辑 我尝试将img重塑为(1,784)并且它也失败了,给出了与此问题标题相同的错误

感谢您的帮助,并就如何添加问题留下评论.

Answer 1

您要求神经网络评估784个案例,每个案例一个输入,而不是单个案例,784个输入.我有同样的问题,我解决了它有一个单元素的数组,这是一个输入数组.请参阅下面的示例,第一个可以正常工作,而第二个给出您遇到的相同错误.

model.predict(np.array([[0.5, 0.0, 0.1, 0.0, 0.0, 0.4, 0.0, 0.0, 0.1, 0.0, 0.0]]))
model.predict(np.array([0.5, 0.0, 0.1, 0.0, 0.0, 0.4, 0.0, 0.0, 0.1, 0.0, 0.0]))

希望这也为你解决它:)