ShuffleNetV2 centernet

最新推荐文章于 2024-08-01 21:07:10 发布

AI算法网奇

最新推荐文章于 2024-08-01 21:07:10 发布

阅读量3k

点赞数

CC 4.0 BY-SA版权

分类专栏：深度学习宝典

本文链接：https://blog.youkuaiyun.com/jacke121/article/details/93083687

深度学习宝典专栏收录该内容

1041 篇文章 ¥29.90 ¥99.00

订阅专栏

超级会员免费看

本文介绍了作者在使用ShuffleNetV2架构优化后的Centernet模型进行训练时遇到的问题，包括训练过程中内存占用过大以及模型未能成功收敛的情况。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

自己改的，用的yolov3的上采样，训练内存很大，也没有收敛

#coding=utf-8
from collections import OrderedDict

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

def _make_divisible(v, divisor, min_value=None):
    """
    This function is taken from the original tf repo.
    It ensures that all layers have a channel number that is divisible by 8
    It can be seen here:
    https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet.py
    :param v:
    :param divisor:
    :param min_value:
    :return:
    """
    if min_value is None:
        min_value = divisor
    new_v = max(min_value, int(v + divisor / 2.0) // divisor * divisor)
    # Make sure that round down does not go dow

了解本专栏