MXnet无法保存网络的所有参数

MXnet公司

我在学MXnet https://gluon-cv.mxnet.io/index.html )。为了从工程师那里学习编程技能,我用 .我用来初始化这个类的参数与官方的相同 网络 .

from gluoncv.model_zoo.ssd import SSD
import mxnet as mx
name = 'resnet50_v1'
base_size = 512
features=['stage3_activation5', 'stage4_activation2']
filters=[512, 512, 256, 256]
sizes=[51.2, 102.4, 189.4, 276.4, 363.52, 450.6, 492]
ratios=[[1, 2, 0.5]] + [[1, 2, 0.5, 3, 1.0/3]] * 3 + [[1, 2, 0.5]] * 2
steps=[16, 32, 64, 128, 256, 512]
classes=('car', 'pedestrian', 'truck', 'trafficLight', 'biker')

pretrained=True

net = SSD(network = name, base_size = base_size, features = features, 
          num_filters = filters, sizes = sizes, ratios = ratios, steps = steps,
              pretrained=pretrained, classes=classes)

数据X

x = mx.nd.zeros(shape=(batch_size,3,base_size,base_size))
cls_preds, box_preds, anchors = net(x)

RuntimeError: Parameter 'ssd0_expand_trans_conv0_weight' has not been initialized. Note that you should initialize parameters and create Trainer with Block.collect_params() instead of Block.params because the later does not include Parameters of nested child Blocks

这是合理的。SSD使用功能 在“”上添加新层_ _我忘了初始化它们。所以,我使用以下代码。

net.initialize()

  v.initialize(None, ctx, init, force_reinit=force_reinit)
C:\Users\Bird\AppData\Local\conda\conda\envs\ssd\lib\site-packages\mxnet\gluon\parameter.py:687: UserWarning: Parameter 'ssd0_resnetv10_stage4_batchnorm9_running_mean' is already initialized, ignoring. Set force_reinit=True to re-initialize.
  v.initialize(None, ctx, init, force_reinit=force_reinit)
C:\Users\Bird\AppData\Local\conda\conda\envs\ssd\lib\site-packages\mxnet\gluon\parameter.py:687: UserWarning: Parameter 'ssd0_resnetv10_stage4_batchnorm9_running_var' is already initialized, ignoring. Set force_reinit=True to re-initialize.
  v.initialize(None, ctx, init, force_reinit=force_reinit)

的 “这是SSD的基础,因此无法安装这些参数。然而,这些警告很烦人。

不过,在这里,

net.save_params('F:/Temps/Models_tmp/' +'myssd.params')

的参数文件_ 97.7毫巴 9.96兆字节

为了测试这项新技术,我打开了 一个新的控制台 重建同一个网络。然后,我加载保存的参数并向其提供数据。

net.load_params('F:/Temps/Models_tmp/' +'myssd.params')
x = mx.nd.zeros(shape=(batch_size,3,base_size,base_size)) 

初始化错误再次出现 .

运行时错误:参数'ssd0_expand_trans_conv0_weight'尚未初始化。请注意,您应该初始化参数并使用block.collect_params()而不是block.params创建trainer,因为后者不包括嵌套子块的参数。

这是不正确的,因为保存的文件'mysd.params'应包含我的网络的所有已安装参数。

找到街区_ SSD0_展开_trans_conv0 _,我在__做了更深入的研究 Gluoncv.nn.特性。功能扩展器 _ _我用__ mxnet.胶子。神经传导二维 _ MX.SYM.卷积 __中的_ 功能扩展器 _

'''
        y = mx.sym.Convolution(
            y, num_filter=num_trans, kernel=(1, 1), no_bias=use_bn,
            name='expand_trans_conv{}'.format(i), attr={'__init__': weight_init})
        '''
        Conv1 = nn.Conv2D(channels = num_trans,kernel_size = (1, 1),use_bias = use_bn,weight_initializer = weight_init)
        y = Conv1(y)
        Conv1.initialize(verbose = True)
    '''    
    y = mx.sym.Convolution(
        y, num_filter=f, kernel=(3, 3), pad=(1, 1), stride=(2, 2),
        no_bias=use_bn, name='expand_conv{}'.format(i), attr={'__init__': weight_init})
    '''
    Conv2 = nn.Conv2D(channels = f,kernel_size = (3, 3),padding = (1, 1),strides = (2, 2),use_bias = use_bn, weight_initializer = weight_init)
    y = Conv2(y)
    Conv2.initialize(verbose = True)

这些新块可以手动初始化。然而,MXnet仍然报告 同样的错误 . 手动初始化似乎没有效果。

如何保存网络的所有参数并恢复它们?