问题
We have a data set that is converted from signal data to video. We want to classify these images using convolution. We tried many different methods but val acc is consistently low. Training accuracy is 99% and val_acc is 40%. We need your help in this respect. Thank you
weight_decay=0.0005
input_ = Input(shape=(125, 125, 1))
# Block 1
x = Conv2D(64, (3, 3), strides=(1, 1), activation='relu', padding='same')(input_)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='pool1')(x)
# Block 2
x = Conv2D(128, (3, 3), strides=(1, 1), activation='relu', padding='same')(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='pool2')(x)
# Block 3
x = Conv2D(256, (3, 3), strides=(1, 1), activation='relu', padding='same')(x)
x = BatchNormalization()(x)
x = Conv2D(256, (3, 3), strides=(1, 1), activation='relu', padding='same')(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='pool3')(x)
# Block 4
x = Conv2D(512, (3, 3), strides=(1, 1), activation='relu', padding='same')(x)
x = BatchNormalization()(x)
x = Conv2D(512, (3, 3), strides=(1, 1), activation='relu', padding='same')(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), padding='same', name='pool4')(x)
x = GlobalMaxPooling2D()(x)
x = Dense(800)(x)
x = BatchNormalization()(x)
x = Dense(800)(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dense(8)(x)
x = Activation('softmax')(x)
model = Model(inputs = input_, outputs=x)
enter image description here
my kernel and dataset https://www.kaggle.com/ultrasonraporlama/video-kernel/
来源：https://stackoverflow.com/questions/59540574/val-accuracy-val-acc-very-low