- 博客(382)
- 资源 (2)
- 收藏
- 关注
原创 口红销量预测--R语言数据挖掘
具体pdf文档,word文档,源数据文档,R源代码参见下面的链接https://download.csdn.net/download/mr_muli/10662137 **口红销量预测--R语言数据挖掘**...
2019-07-14 11:14:58 4921 2
原创 深度学习的小结
迁移学习的定义:在 ImageNet 已经得到一个预训练好的 ConvNet 网络,删除网络的最后一个全连接层,然后将 ConvNet 网络的剩余部分作为新数据集的特征提取层。一旦你提取了所有图像的特征,就可以开始训练新数据集分类器。微调:更换并重新训练 ConvNet 的网络层,还可以通过反向传播算法对预训练网络的权重进行微调。...
2019-05-26 20:57:42 883
原创 Image Annotation图像标注小结
1:标签关系----《Learning Structured Inference Neural Networks with Label Relations》2016–黄鹤翔–邓志伟–学习具有标签关系的结构化推理神经网络标签之间是有一定关系的;标签之间的关系可以形成一个复杂的网络;可以形成不同层次的解释来表示这样的图像模型的要求包括:(1)能够对标签-标签关系(如正相关或负相关)建模;(2)...
2019-05-10 10:34:03 3174 8
转载 深度学习的一些总结
转载:16组-Going Deeper with Convolutions 阅读笔记 **链接:**https://www.jianshu.com/p/ae5c9a0db8b9
2019-04-29 14:38:07 340
原创 ubantu16.04常见命令
sudo chmod -R 777 路径 (文件夹或文件) - import tensorflow as tf - tf.__version__GPU需要加上这句话 os.environ[‘CUDA_VISIBLE_DEVICES’]=‘0’文件比较器: Meldpython2命令:pip2python2...
2019-04-01 09:45:31 354
原创 Image Caption图像描述总结
现有的解决图像描述任务的算法大致可以分为三类 :基于模板式的 、基于相似空间检索式的 、基于多模翻译式的 。现有的生成图像描述的形式大致也可分为三类 :单 句子式描述 ,密集型描述,多语言描述。...
2019-03-18 14:28:36 5839
原创 解决报错No module named ‘utils.typing‘
解决报错No module named ‘utils.typing’ 和 module ‘utils’ has no attribute ‘TensorOrSequence’将拷贝最外层的utils文件夹!
2023-07-28 17:31:54 324
原创 解决报错ModuleNotFoundError: No module named ‘skimage‘
解决报错ModuleNotFoundError: No module named ‘skimage’
2023-07-25 15:50:43 381
原创 解决报错ModuleNotFoundError: No module named ‘inplace_abn‘
报错如下:ModuleNotFoundError: No module named 'inplace_abn'安装:sudo pip install inplace_abn如果安装inplace_abn报错如下:distutils.errors.DistutilsError: Could not find suitable distribution forRequirement.parse('setuptools_scm')---Command "python setup.py egg
2022-03-11 10:41:51 6175 6
原创 AttributeError: module ‘torch.nn‘ has no attribute ‘GELU‘
class GELU(nn.Module): def forward(self, input): return F.gelu(input)nn.GELU() ⇒ GELU()
2021-12-25 10:46:29 4669
原创 利用try-except解决数据流破损的问题
解决数据流破损的问题 def get(self, item): filename = item['file_name']# print("item['labels']: ", item['labels']) # item['labels']: [2, 36, 9, 49, 21] labels = sorted(item['labels']) # 排序# print("labels: ", labels )
2021-11-18 22:20:14 658
原创 python代码实现global top-k pooling
python代码实现global top-k pooling:#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Sat Sep 11 11:25:46 2021@author: muli"""import torchfrom torch import nnclass TopKPool(nn.Module): def __init__(self, k): super(TopKPool, self
2021-09-11 20:13:07 1054
原创 category-wise max-pooling 操作案例理解
案例:import torchimport numpy as npimport random# 设定种子数random.seed(1234) np.random.seed(1234)torch.manual_seed(1234) # cputorch.cuda.manual_seed(1234) # gpuscores = torch.randn(4, 2, 5).cuda() # 2为batch_sizeprint("scores: ", scores
2021-03-17 16:15:48 362
原创 torch.max函数比较最大值
新建两个tensor列表,利用torch.max()进行两个列表的比较:import torcha=torch.tensor([1,2,3,4,5])print("a: ", a)b=torch.tensor([10,1,7,9,3])print("b: ", b)x=torch.max(a,b)print("x: ", x)比较结果如下:# a: tensor([1, 2, 3, 4, 5])# b: tensor([10, 1, 7, 9, 3])# x:
2021-03-17 14:15:17 1389 1
原创 解决报错:TypeError: log_sigmoid(): argument ‘input‘ (position 1) must be Tensor, not torch.return_types.
报错如下:TypeError: log_sigmoid(): argument 'input' (position 1) must be Tensor, not torch.return_types.maxtorch.max()的返回类型为 torch.return_types.maxfused_scores = torch.max(scores, 0)查看 fused_scores 的输出fused_scores: torch.return_types.max(values=tensor
2021-02-02 11:51:37 5162
原创 解决报错 RuntimeError: cuda runtime error (100) : no CUDA-capable device is detected at /pytorch/aten/sr
报错如下:RuntimeError: cuda runtime error (100) : no CUDA-capable device is detected at /pytorch/aten/src/THC/THCGeneral.cpp:47对于单GPU的服务器os.environ["CUDA_VISIBLE_DEVICES"] = '0'报以上的错误,可能是由于未设置成 0
2021-01-25 09:43:55 1830 1
原创 解决报错:IOError: broken data stream when reading image file
加载图片"Corrupt JPEG data: premature end of data segment" 的解决方法raise self.exc_type(msg) OSError: Caught OSError in DataLoader worker process 5.PermissionError: [Errno 13] Permission denied: ‘/usr/lib/python3/dist-packages/PIL’ -> ‘/tmp/pip-uninstall-srp
2021-01-24 09:43:19 2512
原创 python3.6+torch1.6环境安装
记录一下:python3.6+torch1.6环境安装pip install torch==1.6.0+cu101 torchvision==0.7.0+cu101 torchaudio==0.6.0 -f https://download.pytorch.org/whl/torch_stable.html
2021-01-10 19:59:03 2463
原创 python里面读取h5文件报错OSError: Can‘t read data (address of object past end of allocation)
报错如下: File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper File "h5py/h5d.pyx", line 182, in h5py.h5d.DatasetID.read File "h5py/_proxy.pyx", line 158, in h5py._p
2021-01-02 23:25:21 3221 1
原创 python绘制t-SNE算法图--已给输入数据
import numpy as npimport matplotlib.pyplot as pltfrom sklearn import manifoldX = [[0.31098375, 0.60610425], [0.889303 , 0.43060997], [0.59896564 ,0.25923628], [0.8858032 , 0.5066341 ], [0.4451317 ,0.10089866], [0.4884346 ,0.1294026 ], [0.167
2021-01-01 13:05:29 1482
原创 t-SNE手写字识别案例
参考链接:https://scikit-learn.org/stable/auto_examples/manifold/plot_lle_digits.html#sphx-glr-auto-examples-manifold-plot-lle-digits-py代码如下:#!/usr/bin/env python3# -*- coding: utf-8 -*-"""Created on Wed Dec 23 22:47:54 2020@author: muli"""from time
2020-12-23 22:54:36 259
原创 导入spacy时报错OSError: [E050] Can‘t find model ‘en‘. It doesn‘t seem to be a shortcut link,
报错如下: File "/home/muli/.local/lib/python3.6/site-packages/spacy/util.py", line 175, in load_model raise IOError(Errors.E050.format(name=name))OSError: [E050] Can't find model 'en'. It doesn't seem to be a shortcut link, a Python package or a valid p
2020-12-23 16:07:10 1393 1
原创 解决报错:ModuleNotFoundError: No module named ‘neptune‘
解决报错:ModuleNotFoundError: No module named ‘neptune’sudo pip install neptune_client -i https://pypi.tuna.tsinghua.edu.cn/simple
2020-11-29 22:56:13 1686
原创 报错:RuntimeError: cuda runtime error (100) : no CUDA-capable device is detected at /pytorch/aten/src/
no CUDA-capable device ,可能原因时没有torch-GPU在代码中指定了GPU(多卡情况下),而单卡中是 ‘0’ os.environ["CUDA_VISIBLE_DEVICES"] = '1' 将 os.environ[“CUDA_VISIBLE_DEVICES”] = ‘1’ 修改为 os.environ["CUDA_VISIBLE_DEVICES"] = '0' 或者注释该行代码最后,附上pytorch自查代码:..
2020-11-03 21:38:26 5070
原创 tensorflow-gpu与cuda、keras之间的对应关系
tensorflow-gpu与cuda之间的对应关系:tensorflow与Keras之间的对应关系
2020-10-16 15:04:59 5002 1
原创 解决ubantu16.04里面由python3.5升级到python3.6报错Unable to locate package python3.6
报错如下:Reading package lists... DoneBuilding dependency tree Reading state information... DoneE: Unable to locate package python3.6E: Couldn't find any package by glob 'python3.6'E: Couldn't find any package by regex 'python3.6'使用的ppa是旧版本:sud
2020-10-02 14:34:12 3546 2
原创 解决报错AttributeError: ‘collections.defaultdict‘ object has no attribute ‘iteritems‘
报错如下:AttributeError: 'collections.defaultdict' object has no attribute 'iteritems'由于python2和python3版本之间的差异,将 x.iteritems() 替换为 x.items() 即可
2020-09-29 20:16:17 3303
原创 解决from pyemd import emd ModuleNotFoundError: No module named ‘pyemd‘
报错如下: File "/usr/local/lib/python3.6/dist-packages/gensim/models/keyedvectors.py", line 717, in wmdistance from pyemd import emdModuleNotFoundError: No module named 'pyemd'第一步: sudo pip install pyemd==0.5.1 ,报错如下: error: command ‘x86_64-linux-gnu
2020-09-22 14:11:40 3359 1
原创 self.fp = open(file, modeDict[mode]) IOError: [Errno 2] No such file or directory:
报错如下: File "/usr/lib/python2.7/dist-packages/numpy/lib/npyio.py", line 92, in zipfile_factory return zipfile.ZipFile(*args, **kwargs) File "/usr/lib/python2.7/zipfile.py", line 756, in __init__ self.fp = open(file, modeDict[mode])IOError: [Er
2020-09-21 14:29:25 1376 2
原创 if self.dataset[‘type‘] == ‘instances‘: KeyError: ‘type‘
报错如下: File "/××××××××××/coco-caption/pycocotools/coco.py", line 100, in createIndex if self.dataset['type'] == 'instances':KeyError: 'type'由于python版本原因,将 if self.dataset['type'] == 'instances':替换为:if type(self.dataset) == 'instances':...
2020-09-20 14:59:59 940 1
原创 ModuleNotFoundError: No module named ‘pycocoevalcap‘
安装gitsudo apt-get install git安装pycocoevalcappip install "git+https://github.com/salaniz/pycocoevalcap.git"
2020-09-19 21:55:00 3535 3
原创 设置word2016默认的字体和大小
新建word文档后,操作如下:打开段落设置中文字体格式设置中文字体大小设置英文字体格式和大小点击“设置默认值”设置为所有文档点击 确定因此,在新建所有word文档时,所有字体的默认格式为上述设置。例如,博主的为 “宋体-5号”...
2020-04-20 16:13:32 3401
原创 python绘制折线图--纵坐标y轴截断
python绘制折线图–纵坐标y轴截断# -*- coding: utf-8 -*-"""Created on Wed Dec 4 21:50:38 2019@author: muli"""import matplotlib.pyplot as pltfrom pylab import * mpl.rcParams['font.sans-ser...
2019-12-05 09:15:53 9863
原创 【Tensorflow slim】读取vgg16和inception_v3的params和FLOPs
【Tensorflow slim】读取vgg16和inception_v3的params和FLOPs#coding = utf-8 import tensorflow as tfimport tensorflow.contrib.slim as slimfrom tensorflow.contrib.slim.nets import vggfrom tensorflow.contrib...
2019-12-04 09:50:19 922
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人