model.save_weights('weights', save_format='h5')

model.load_weights('weights', by_name=True)

class ResNet(models.Model):def __init__(self, layer_num, **kwargs):super(ResNet, self).__init__(**kwargs)if block_type[layer_num] == 'basic block':self.block = BasicBlockelse:self.block = BottleneckBlockself.conv0 = Conv2D(64, (7, 7), strides=(2, 2), name='conv0', padding='same', use_bias=False)self.block_collector = []for layer_index, (b, f) in enumerate(zip(block_num[layer_num], filter_num), start=1):if layer_index == 1:if block_type[layer_num] == 'basic block':self.block_collector.append(self.block(f, name='conv1_0'))else:self.block_collector.append(self.block(f, projection=True, name='conv1_0'))else:self.block_collector.append(self.block(f, strides=(2, 2), name='conv{}_0'.format(layer_index)))for block_index in range(1, b):self.block_collector.append(self.block(f, name='conv{}_{}'.format(layer_index, block_index)))self.bn = BatchNormalization(name='bn', momentum=0.9, epsilon=1e-5)self.global_average_pooling = GlobalAvgPool2D()self.fc = Dense(1000, name='fully_connected', activation='softmax', use_bias=False)def call(self, inputs, training):net = self.conv0(inputs)print('input', inputs.shape)print('conv0', net.shape)net = tf.nn.max_pool2d(net, ksize=(3, 3), strides=(2, 2), padding='SAME')print('max-pooling', net.shape)for block in self.block_collector:net = block(net, training)print(block.name, net.shape)net = self.bn(net, training)net = tf.nn.relu(net)net = self.global_average_pooling(net)print('global average-pooling', net.shape)net = self.fc(net)print('fully connected', net.shape)return net