python - Keras 值错误 : Dimensions must be equal

Question

该模型的目标是根据与视频输入相关联的单词对视频输入进行分类。每个输入的维度为 45 帧、1 个灰色 channel 、100 像素行和 150 像素列(45、1、100、150)，而每个对应的输出是 3 个可能单词之一的单热编码表示(例如"is"=> [0, 0, 1]).

模型编译过程中，出现如下错误:

ValueError: Dimensions must be equal, but are 1 and 3 for 'Conv2D_94' (op: 'Conv2D') with 
input shapes: [?,100,150,1], [3,3,3,32].

这是用于训练模型的脚本:

video = Input(shape=(self.frames_per_sequence,
                     1,
                     self.rows,
                     self.columns))
cnn = InceptionV3(weights="imagenet",
                  include_top=False)
cnn.trainable = False
encoded_frames = TimeDistributed(cnn)(video)
encoded_vid = LSTM(256)(encoded_frames)
hidden_layer = Dense(output_dim=1024, activation="relu")(encoded_vid)
outputs = Dense(output_dim=class_count, activation="softmax")(hidden_layer)
osr = Model([video], outputs)
optimizer = Nadam(lr=0.002,
                  beta_1=0.9,
                  beta_2=0.999,
                  epsilon=1e-08,
                  schedule_decay=0.004)
osr.compile(loss="categorical_crossentropy",
            optimizer=optimizer,
            metrics=["categorical_accuracy"]) 

Answer 1

根据 Convolution2D在 Keras 中，下面应该是输入和过滤器的形状。

shape of input = [batch, in_height, in_width, in_channels]
shape of filter = [filter_height, filter_width, in_channels, out_channels]

所以，你得到的错误的含义 -

ValueError: Dimensions must be equal, but are 1 and 3 for 'Conv2D_94' (op: 'Conv2D') with 
input shapes: [?,100,150,1], [3,3,3,32].

[?,100,150,1] 表示 in_channels 值为 1 而 [3,3,3,32] 表示 in_channels 值为 3。这就是您收到错误的原因 - Dimensions must be equal, but are 1 and 3。

因此您可以将过滤器的形状更改为[3, 3, 1, 32]。