我想用Keras来建立一个CNN-LSTM网络.但是,我很难为第一个层的input_shape参数找到正确的形状。我的train_data是形状为(1433, 32, 32)的ndarray;尺寸为32x32的1433张图片。正如在中所发现的,我尝试使用input_shape=train_data.shape[1:],这会导致与input_shape=train_data.shape相同的错误
I
time series input/output datamodel.add(LSTM(units=256, return_sequences=True, input_shape如果我正确理解了,通过具有多个特性,我需要使用Conv2D,而不是Conv1D,但是如果我设置了Conv2D(padding='causal'),我会得到以下错误- Invalid padding: causal)
无论如何,我还能够用一个新的形状(number of examples, lo
摘要ValueError: Error when checking : expected lstm_13_input to have shape (None, 40, 39) but got, 40, 39) but got array with shape (1, 39, 39)我曾经玩过由它产生的seed_string 和 x 的维度</
input: expected lstm_40_input to have shape (1, 10000) but got array with shape (10000, 1)ValueError: Error when checking target: expected dense_39 to have shapenp.reshape(x, (33, 10000, 1))
regressor.