小编yam*_*oel的帖子

我正在使用深度神经网络模型（在 中实现keras）进行预测。像这样的东西：

def make_model():
 model = Sequential()       
 model.add(Conv2D(20,(5,5), activation = "relu"))
 model.add(MaxPooling2D(pool_size=(2,2)))    
 model.add(Flatten())
 model.add(Dense(20, activation = "relu"))
 model.add(Lambda(lambda x: tf.expand_dims(x, axis=1)))
 model.add(SimpleRNN(50, activation="relu"))
 model.add(Dense(1, activation="sigmoid"))    
 model.compile(loss = "binary_crossentropy", optimizer = adagrad, metrics = ["accuracy"])

 return model

model = make_model()
model.fit(x_train, y_train, validation_data = (x_validation,y_validation), epochs = 25, batch_size = 25, verbose = 1)

##Prediciton:
prediction = model.predict_classes(x)
probabilities = model.predict_proba(x) #I assume these are the probabilities of class being predictied

我的问题是分类（二进制）问题。我希望计算其中每一个的置信度得分，prediction即我想知道 - 我的模型是 99% 确定它是“0”还是 58% …

我收到错误：ValueError: Input 0 is incompatible with layer lstm_1: expected ndim=3, found ndim=2使用以下代码：

def make_model():
  model = Sequential()      

  model.add(Conv2D(20,(5,5), input_shape = (24,48,30), activation = "relu", strides = 1, padding = "valid"))
  model.add(MaxPooling2D(pool_size=(2,2)))        
  model.add(Conv2D(50, (5,5), use_bias = 50))    
  model.add(MaxPooling2D(pool_size=(2,2)))    
  model.add(Flatten())
  model.add(Dense(20, activation = "relu"))
  model.add(LSTM(50, activation="relu", return_sequences=True))

  return model

我的输入是 30 个大小为 24*48 的矩阵。

我需要添加各列的行值并将其存储在相同（或新）数据框中。例如：数据框看起来像这样：

id  col1  col2  col3  col4 ...  col50
 1    1     12    3     44         0
 1    7      0    7      2         10
 1    2      3    0      4         9
 3    9      0    1      0         0
 3    1      1   11      1         0

预期值应该是：

id  col1  col2  col3  col4...  col50
 1    10   15    10    46        19
 3    10    1    12     1         0

如果我使用tmp2 = tmp2.iloc[:,1:50].sum()，它会改变数据框的尺寸。

我有一个创建.csv文件的 python 脚本。

当我尝试通过以下方式下载脚本中的文件Vectors.csv（由代码创建的文件）时

df.to_csv("Vectors.csv", sep=",", index=False)
files.download("Vectors.csv")  

我明白了

Traceback (most recent call last):
File "/content/gdrive/My Drive/Deep/makeVectors.py", line 52, in <module>
files.download("Vectors.csv")
File "/usr/local/lib/python3.6/dist-packages/google/colab/files.py", line 178, in download
'name': _os.path.basename(filename),
File "/usr/local/lib/python3.6/dist-packages/google/colab/output/_js.py", line 35, in eval_js
kernel = _ipython.get_kernel()
File "/usr/local/lib/python3.6/dist-packages/google/colab/_ipython.py", line 28, in get_kernel
return get_ipython().kernel
AttributeError: 'NoneType' object has no attribute 'kernel'

然而，当我在 Colab 单元格中键入相同的命令时，它工作得很好。

浏览器：谷歌浏览器