pytorch中获取模型input/outputshape实例-创新互联

Pytorch官方目前无法像tensorflow, caffe那样直接给出shape信息，详见

https://github.com/pytorch/pytorch/pull/3043

以下代码算一种workaround。由于CNN, RNN等模块实现不一样，添加其他模块支持可能需要改代码。

例如RNN中bias是bool类型，其权重也不是存于weight属性中，不过我们只关注shape够用了。

该方法必须构造一个输入调用forward后（model(x)调用）才可获取shape

#coding:utf-8
from collections import OrderedDict
import torch
from torch.autograd import Variable
import torch.nn as nn
import models.crnn as crnn
import json
 
 
def get_output_size(summary_dict, output):
 if isinstance(output, tuple):
 for i in xrange(len(output)):
  summary_dict[i] = OrderedDict()
  summary_dict[i] = get_output_size(summary_dict[i],output[i])
 else:
 summary_dict['output_shape'] = list(output.size())
 return summary_dict
 
def summary(input_size, model):
 def register_hook(module):
 def hook(module, input, output):
  class_name = str(module.__class__).split('.')[-1].split("'")[0]
  module_idx = len(summary)
 
  m_key = '%s-%i' % (class_name, module_idx+1)
  summary[m_key] = OrderedDict()
  summary[m_key]['input_shape'] = list(input[0].size())
  summary[m_key] = get_output_size(summary[m_key], output)
 
  params = 0
  if hasattr(module, 'weight'):
  params += torch.prod(torch.LongTensor(list(module.weight.size())))
  if module.weight.requires_grad:
   summary[m_key]['trainable'] = True
  else:
   summary[m_key]['trainable'] = False
  #if hasattr(module, 'bias'):
  # params += torch.prod(torch.LongTensor(list(module.bias.size())))
 
  summary[m_key]['nb_params'] = params
  
 if not isinstance(module, nn.Sequential) and \
  not isinstance(module, nn.ModuleList) and \
  not (module == model):
  hooks.append(module.register_forward_hook(hook))
 
 # check if there are multiple inputs to the network
 if isinstance(input_size[0], (list, tuple)):
 x = [Variable(torch.rand(1,*in_size)) for in_size in input_size]
 else:
 x = Variable(torch.rand(1,*input_size))
 
 # create properties
 summary = OrderedDict()
 hooks = []
 # register hook
 model.apply(register_hook)
 # make a forward pass
 model(x)
 # remove these hooks
 for h in hooks:
 h.remove()
 
 return summary
 
crnn = crnn.CRNN(32, 1, 3755, 256, 1)
x = summary([1,32,128],crnn)
print json.dumps(x)

另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。