最近我一直在比较 vgg16 和 resnetv1 的 20 层。我发现虽然 vgg 上的每个 epoch 需要更多时间来完成，但通常比 resnet20 需要更少的 epoch 才能达到一定的训练精度。为什么 vgg 学得更快？我的实验正确吗？我已经在 Cifar100 和一部分 imagenet 上尝试过（来自 stanford cv course 的小图像网）

vgg 有近 14m 的参数，但 resnet 只有 0.3m。这是我对重新发送的实现：

def resnet_layer1(inputs,initializer,
             num_filters=16,
             kernel_size=3,
             strides=1,
             activation='relu',
             conv_first=True,batch_normalization=True):


conv = Conv2D(num_filters,
              kernel_size=kernel_size,
              strides=strides,
              padding='same',
              kernel_initializer=initializer
             )

x = inputs
if conv_first:
    x = conv(x)
    if batch_normalization:
        x = BatchNormalization()(x)
    x = Activation(activation)(x)
else:
    if batch_normalization:
        x = BatchNormalization()(x)
    x = Activation(activation)(x)
    x = conv(x)
return x
def resnet_1(model_number,x_train,y_train,x_test,y_test,datagen,initializer,epochs=20,bs=512,output_nodes=10,optim='adam',padding='same',dout=True,callbacks=None):

depth=20
# Start model definition.
num_filters = 16
num_res_blocks = int((depth - 2) / 6)


if model_number == 1:
    resnet_layer=resnet_layer1
elif model_number == 2:
    resnet_layer=resnet_layer2
elif model_number == 3:
    resnet_layer=resnet_layer3
elif model_number == 4:
    resnet_layer=resnet_layer4

inputs = Input(shape=x_train.shape[1:])
x = resnet_layer(inputs=inputs,initializer=initializer)
# Instantiate the stack of residual units
for stack in range(3):
    for res_block in range(num_res_blocks):
        strides = 1
        if stack > 0 and res_block == 0:  # first layer but not first stack
            strides = 2  # downsample
        y = resnet_layer(inputs=x,initializer=initializer,
                         num_filters=num_filters,
                         strides=strides)
        y = resnet_layer(inputs=y,initializer=initializer,
                         num_filters=num_filters,
                         activation=None)
        if stack > 0 and res_block == 0:  # first layer but not first stack
            # linear projection residual shortcut connection to match
            # changed dims
            x = resnet_layer(inputs=x,initializer=initializer,
                             num_filters=num_filters,
                             kernel_size=1,
                             strides=strides,
                             activation=None,
                             batch_normalization=False)
        x = layers.add([x, y])
        x = Activation('relu')(x)
    num_filters *= 2

# Add classifier on top.
# v1 does not use BN after last shortcut connection-ReLU
x = AveragePooling2D(pool_size=8)(x)
y = Flatten()(x)
outputs = Dense(output_nodes,
                activation='softmax',
                kernel_initializer=initializer)(y)

# Instantiate model.
model = Model(inputs=inputs, outputs=outputs)
model.summary()
# Compile the model
model.compile(loss=['categorical_crossentropy'], optimizer=optim, metrics=["accuracy"])

checkpointer = ModelCheckpoint(filepath=str(model_number)+'_weights.hdf5', verbose=1,save_weights_only=True,save_freq=2000000)

callbacks.append(checkpointer)

if x_test.all() == None:
    history=model.fit_generator(datagen.flow(x_train, y_train,batch_size=bs),callbacks=callbacks,epochs=epochs, steps_per_epoch=x_train.shape[0]//bs)
else:
    history=model.fit_generator(datagen.flow(x_train, y_train,batch_size=bs),callbacks=callbacks,epochs=epochs,validation_data=(x_test, y_test), steps_per_epoch=x_train.shape[0]//bs)

return history,model