JinfengZhang

按操作步骤生成了70000张数据pair，补充进oulu p1进行训练但训练DUM收敛效果很差，不知道什么原因 

您好，想请问一下网络搜索完之后如何得到需要的网络结构代码？

3

在网络搜索完后，得到的最高精度网络结构为genotype = Genotype(normal=[('sep_conv_5x5', 1), ('dil_conv_3x3', 0), ('dil_conv_5x5', 2), ('sep_conv_3x3', 1), ('avg_pool_3x3', 3), ('avg_pool_3x3', 1), ('sep_conv_5x5', 1), ('dil_conv_5x5', 4)], normal_concat=range(2, 6), reduce=[('sep_conv_5x5', 1), ('dil_conv_3x3', 0), ('sep_conv_5x5', 2), ('sep_conv_5x5', 1), ('dil_conv_5x5', 2),...

File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker output = module(*input, **kwargs) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, **kwargs) File "/home/model_search.py", line 159, in forward s0, s1 = s1,...

can't test?

1

LocalFileSystem: fail to open "../deploy/mtcnn-model/det1-symbol.json"

请问mobilenext转onnx可以吗？我转完onnx过程没有报错但是和pytorch输出对不上

2

我转onnx的代码如下： onnx版本是1.6.0 import torch import os import numpy as np from model.mobilenext import mnext def main(): initial_checkpoint = 'mobiilenext_se.pth' network = mnext(num_classes=2) network.eval() state = torch.load(initial_checkpoint, map_location=lambda storage, loc: storage)...