espnetv2

效果比dicenet稍微好一点,不知道为什么

https://blog.csdn.net/jacke121/article/details/114148435

import os
import time

import torch
from torch import nn

from torch.nn import init
import torch.nn.functional as F


rep_layers = [0, 5, 7, 3]

# limits for the receptive field at each spatial level
recept_limit = [13, 11, 9, 7, 5]
branches = 4

# input reinforcement related parameters
config_inp_reinf = 3
input_reinforcement = True

class CDilated(nn.Module):
    '''
    This class defines the dilated convolution.
    '''

    def __init__(self, nIn, nOut, kSize, stride=1, d=1, groups=1):
        '''
        :param nIn: number of input channels
        :param nOut: number of output channels
        :param kSize: kernel size
        :param stride: optional stride rate for down-sampling
        :param d: optional 
已标记关键词 清除标记
相关推荐
©️2020 CSDN 皮肤主题: Age of Ai 设计师:meimeiellie 返回首页
实付 29.90元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、C币套餐、付费专栏及课程。

余额充值