我正在尝试使用Keras神经网络来识别画在画布上的数字图像，并输出相应的数字。我已经保存了神经网络，并使用Django来运行Web界面。但每次运行时，我都会遇到内部服务器错误，并且在服务器端代码中出现错误。错误信息显示异常：检查时出错：期望dense_input_1的形状为(None, 784)，但得到的数组形状为(784, 1)。我的主要视图是
from django.shortcuts import renderfrom django.http import HttpResponseimport StringIOfrom PIL import Imageimport numpy as npimport refrom keras.models import model_from_jsondef 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")我查看了以下链接：
编辑根据Rohan的建议，这是我的堆栈跟踪
内部服务器错误：/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 homeoutput=loaded_model.predict(img_np) File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 671, in predictreturn 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 predictcheck_batch_dim=False) File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 108, in standardize_input_datastr(array.shape))Exception: Error when checking : expected dense_input_1 to have shape (None, 784) but got array with shape (784, 1)另外，我有最初用来训练网络的模型。
import numpyfrom keras.datasets import mnistfrom keras.models import Sequentialfrom keras.layers import Densefrom keras.layers import Dropoutfrom keras.utils import np_utils# fix random seed for reproducibilityseed = 7numpy.random.seed(seed)(X_train, y_train), (X_test, y_test) = mnist.load_data()for item in y_train.shape: print itemnum_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 0-1X_train = X_train / 255X_test = X_test / 255print X_train.shape# one hot encode outputsy_train = np_utils.to_categorical(y_train)y_test = np_utils.to_categorical(y_test)num_classes = y_test.shape[1]# define baseline modeldef 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 modelmodel = baseline_model()# Fit the modelmodel.fit(X_train, y_train, validation_data=(X_test, y_test), nb_epoch=20, batch_size=200, verbose=1)# Final evaluation of the modelscores = model.evaluate(X_test, y_test, verbose=0)print("Baseline Error: %.2f%%" % (100-scores[1]*100))# serialize model to JSONmodel_json = model.to_json()with open("model.json", "w") as json_file: json_file.write(model_json)# serialize weights to HDF5model.save_weights("model.h5")print("Saved model to disk")编辑我尝试将图像重塑为(1,784)，但也失败了，出现了与此问题标题相同的信息
感谢帮助，请在评论中告诉我应该如何补充这个问题。
回答：
你要求神经网络评估784个案例，每个案例有一个输入，而不是一个案例有784个输入。我也遇到过同样的问题，我的解决方法是使用一个包含单个元素的数组，而这个元素本身是一个输入数组。请看下面的例子，第一个例子可以工作，而第二个例子会出现你遇到的问题。
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]))希望这也能解决你的问题 🙂
