假设您的预测数组类似于:

Let's say your predictions array is something like:

preds_sigmoid = np.array([[0.8451], [0.454], [0.5111]])

包含这些值的

作为S型，将它们压缩在[0,1]的范围内.当您像以前一样应用 argmax 时，由于 argmax 返回指定轴上的最大索引，因此每次都会获得索引0.

containing these values as sigmoid squeeze them in a range of [0,1]. When you apply argmax as you did, you will get index 0 everytime because argmax returns the maximum index at specified axis.

pred = np.argmax(preds_sigmoid , axis = 1) # pred is full of zeros.

您应该对预测进行评估，例如它是否大于某个阈值，比如说0.5，它属于第二类.您可以为此使用列表理解:

You should evaluate the predictions like if it is bigger than some threshold, let's say 0.5, it belongs to second class. You can use list comprehension for this:

pred = [1 * (x[0]>=0.5) for x in preds_sigmoid]

因此，预测将得到正确处理.

Therefore predictions will be handled properly.