DENSE

最新推荐文章于 2024-08-21 15:50:15 发布
最新推荐文章于 2024-08-21 15:50:15 发布
阅读量547 收藏
点赞数
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_39147616/article/details/89141709
版权

DENSE:
https://blog.csdn.net/u012969412/article/details/70882296

E tensorflow/stream_executor/cuda/cuda_blas.cc:372] failed to create cublas handle: CUBLAS_STATUS_NOT_INITIALIZED
W tensorflow/stream_executor/stream.cc:1390] attempting to perform BLAS operation using StreamExecutor without BLAS support
Traceback (most recent call last):
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”, line 1022, in _do_call
return fn(*args)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”, line 1004, in _run_fn
status, run_metadata)
File “/home/zhangdawei/anaconda3/lib/python3.6/contextlib.py”, line 88, in exit
next(self.gen)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py”, line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InternalError: Blas SGEMM launch failed : a.shape=(2, 18), b.shape=(18, 24), m=2, n=24, k=18
[[Node: lstm_1/MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](lstm_1/Reshape, lstm_1/strided_slice)]]
[[Node: mul_1/_51 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name=“edge_2806_mul_1”, tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/home/zhangdawei/Desktop/Human-Activity-Recognition-master1/main.py”, line 122, in
model.fit(X_train, y_train, epochs=3, batch_size=pow(2,i))
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/models.py”, line 870, in fit
initial_epoch=initial_epoch)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/engine/training.py”, line 1507, in fit
initial_epoch=initial_epoch)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/engine/training.py”, line 1156, in _fit_loop
outs = f(ins_batch)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py”, line 2269, in call
**self.session_kwargs)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”, line 767, in run
run_metadata_ptr)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”, line 965, in _run
feed_dict_string, options, run_metadata)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”, line 1015, in _do_run
target_list, options, run_metadata)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py”, line 1035, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Blas SGEMM launch failed : a.shape=(2, 18), b.shape=(18, 24), m=2, n=24, k=18
[[Node: lstm_1/MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](lstm_1/Reshape, lstm_1/strided_slice)]]
[[Node: mul_1/_51 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name=“edge_2806_mul_1”, tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]

Caused by op ‘lstm_1/MatMul’, defined at:
File “/home/zhangdawei/Desktop/Human-Activity-Recognition-master1/main.py”, line 101, in
model.add(LSTM(24, input_dim = parameters1,return_sequences=True))
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/models.py”, line 443, in add
layer(x)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/layers/recurrent.py”, line 262, in call
return super(Recurrent, self).call(inputs, **kwargs)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py”, line 596, in call
output = self.call(inputs, **kwargs)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/layers/recurrent.py”, line 333, in call
preprocessed_input = self.preprocess_input(inputs, training=None)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/layers/recurrent.py”, line 1077, in preprocess_input
timesteps, training=training)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/layers/recurrent.py”, line 50, in _time_distributed_dense
x = K.dot(x, w)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py”, line 976, in dot
out = tf.matmul(x, y)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py”, line 1765, in matmul
a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py”, line 1454, in _mat_mul
transpose_b=transpose_b, name=name)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py”, line 763, in apply_op
op_def=op_def)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”, line 2327, in create_op
original_op=self._default_original_op, op_def=op_def)
File “/home/zhangdawei/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py”, line 1226, in init
self._traceback = _extract_stack()

InternalError (see above for traceback): Blas SGEMM launch failed : a.shape=(2, 18), b.shape=(18, 24), m=2, n=24, k=18
[[Node: lstm_1/MatMul = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/gpu:0"](lstm_1/Reshape, lstm_1/strided_slice)]]
[[Node: mul_1/_51 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name=“edge_2806_mul_1”, tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]]

4.11
Traceback (most recent call last):
File “/usr/lib/python3.5/tkinter/init.py”, line 36, in
import _tkinter
ImportError: No module named ‘_tkinter’

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/home/zhangdawei/my/Human-Activity-Recognition-master1/main.py”, line 5, in
import matplotlib.pyplot as plt
File “/home/zhangdawei/my/Human-Activity-Recognition-master1/venv/lib/python3.5/site-packages/matplotlib/pyplot.py”, line 2372, in
switch_backend(rcParams[“backend”])
File “/home/zhangdawei/my/Human-Activity-Recognition-master1/venv/lib/python3.5/site-packages/matplotlib/pyplot.py”, line 207, in switch_backend
backend_mod = importlib.import_module(backend_name)
File “/usr/lib/python3.5/importlib/init.py”, line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File “/home/zhangdawei/my/Human-Activity-Recognition-master1/venv/lib/python3.5/site-packages/matplotlib/backends/backend_tkagg.py”, line 1, in
from . import _backend_tk
File “/home/zhangdawei/my/Human-Activity-Recognition-master1/venv/lib/python3.5/site-packages/matplotlib/backends/_backend_tk.py”, line 5, in
import tkinter as Tk
File “/usr/lib/python3.5/tkinter/init.py”, line 38, in
raise ImportError(str(msg) + ‘, please install the python3-tk package’)
ImportError: No module named ‘_tkinter’, please install the python3-tk package

4 12
https://blog.csdn.net/weixin_39147616/article/details/89141709
Get:1 file:/var/cuda-repo-8-0-local-ga2 InRelease
Ign:1 file:/var/cuda-repo-8-0-local-ga2 InRelease
Err:2 https://packages.microsoft.com/repos/vscode stable InRelease
Failed to connect to 127.0.0.1 port 37337: Connection refused
Get:3 file:/var/cuda-repo-8-0-local-ga2 Release [574 B]
Get:3 file:/var/cuda-repo-8-0-local-ga2 Release [574 B]
Err:5 http://archive.canonical.com lucid InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:6 http://dl.google.com/linux/chrome/deb stable InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:7 http://extras.ubuntu.com/ubuntu precise InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:8 http://mirrors.163.com/ubuntu precise InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:9 http://mirrors.163.com/ubuntu precise-updates InRelease
Unable to connect to 127.0.0.1:37337:
Err:10 http://archive.ubuntukylin.com:10006/ubuntukylin xenial InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:11 http://mirrors.163.com/ubuntu precise-backports InRelease
Unable to connect to 127.0.0.1:37337:
Err:12 http://mirrors.163.com/ubuntu precise-security InRelease
Unable to connect to 127.0.0.1:37337:
Err:13 http://mirrors.yun-idc.com/ubuntu xenial InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:14 http://ppa.launchpad.net/chris-lea/libsodium/ubuntu xenial InRelease
Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
Err:15 http://ppa.launchpad.net/graphics-drivers/ppa/ubuntu xenial InRelease
Unable to connect to 127.0.0.1:37337:
Err:16 http://mirrors.yun-idc.com/ubuntu xenial-updates InRelease
Unable to connect to 127.0.0.1:37337:
Err:17 http://mirrors.yun-idc.com/ubuntu xenial-backports InRelease
Unable to connect to 127.0.0.1:37337:
Err:18 http://mirrors.yun-idc.com/ubuntu xenial-security InRelease
Unable to connect to 127.0.0.1:37337:
Reading package lists… Done
W: Failed to fetch http://mirrors.yun-idc.com/ubuntu/dists/xenial/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch http://mirrors.yun-idc.com/ubuntu/dists/xenial-updates/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://mirrors.yun-idc.com/ubuntu/dists/xenial-backports/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://mirrors.yun-idc.com/ubuntu/dists/xenial-security/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://mirrors.163.com/ubuntu/dists/precise/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch http://mirrors.163.com/ubuntu/dists/precise-updates/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://mirrors.163.com/ubuntu/dists/precise-backports/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://mirrors.163.com/ubuntu/dists/precise-security/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://extras.ubuntu.com/ubuntu/dists/precise/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch http://archive.canonical.com/dists/lucid/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch http://ppa.launchpad.net/chris-lea/libsodium/ubuntu/dists/xenial/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch http://dl.google.com/linux/chrome/deb/dists/stable/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch http://ppa.launchpad.net/graphics-drivers/ppa/ubuntu/dists/xenial/InRelease Unable to connect to 127.0.0.1:37337:
W: Failed to fetch http://archive.ubuntukylin.com:10006/ubuntukylin/dists/xenial/InRelease Could not connect to 127.0.0.1:37337 (127.0.0.1). - connect (111: Connection refused)
W: Failed to fetch https://packages.microsoft.com/repos/vscode/dists/stable/InRelease Failed to connect to 127.0.0.1 port 37337: Connection refused
W: Some index files failed to download. They have been ignored, or old ones used instead.

4 13
1 method 1
https://blog.csdn.net/temotemo/article/details/79445694
2 method2
download tkinter bao install by myself
3 method3
caozuo zai python2.7 dan yinggai zai 3.5 xia suyi suoyi caozuo dou shi bai fei

弓长伟大
关注
DenseNet算法详解
AI之路
07-15 29万+
论文：Densely Connected Convolutional Networks 论文链接：https://arxiv.org/pdf/1608.06993.pdf 代码的github链接：https://github.com/liuzhuang13/DenseNet文章详解： 这篇文章是CVPR2017的oral，非常厉害。文章提出的DenseNet（Dense Convolution
Dense Prediction
YQ8023family的博客
03-25 1583
参考 预测图像中每个像素标签的任务
【机器学习】dense的用法以及如何用Numpy构建一个简单神经网络
最新发布
ya的博客
08-21 1270
在实际应用中，需要用实际的训练数据替换x_train和y_train，并设置合适的epochs和batch_size参数来训练模型在NumPy中构建了一个小型神经网络，揭示了构成神经网络中一层的相当简单和熟悉的函数。
DenseNet
weixin_41172694的博客
02-11 8494
版权声明：本文为博主原创文章，未经博主允许不得转载 论文：Densely Connected Convolutional Networks 链接：https://arxiv.org/abs/1608.06993 第三方代码： CVPR2017的最佳论文 论文详解： 作为CVPR2017年的Best Paper, DenseNet脱离了加深网络层数(ResNet)和加宽网络结构(In...
dense graph python实现
11-11
dense-graph的Python实现版，可创建有向图、无向图。 图内包括点的set、边的map、查询边是否存在、点是否存在、获取点/边的位置 点内包括点的key值、边的weight权重、点的value
Python深度学习读书笔记（七）（温度预测问题Dense,GRU,dropout）
DSH自学记录
08-29 3294
循环神经网络的高级技巧：循环dropout ,堆叠循环层, 双向循环层。 GRU层工作原理和LSTM相同，做了简化，运行计算代价更低。 #观察数据集中数据 import os data_dir='D:\\jupyter_code\\jena_climate' fname=os.path.join(data_dir,'jena_climate_2009_2016.csv') f=open...
DenseNet201_densenet_训练模型_densenet201_
09-29
这个模型的核心特点是其稠密连接（Dense Connections）机制，它显著改善了信息流和特征重用，减少了参数数量，提高了模型性能。 ### 1. 稠密连接的概念 在传统的CNN中，每一层的输出通常只传递给下一层。而在Dense...
Densenet121.zip
03-25
《深度学习中的DenseNet121模型在柑橘叶片识别中的应用》 在现代的计算机视觉领域，深度学习已经成为解决复杂图像识别问题的核心技术。本文将深入探讨DenseNet121这一深度学习模型在柑橘叶片识别中的应用，以及如何...
Dense_Haze 浓雾数据集
09-24
CVPR 2019挑战赛Dense_Haze_NTIRE19 浓雾去雾数据集，含55张雾图像与对应的Ground Truth。CVPR 2019挑战赛Dense_Haze_NTIRE19 浓雾去雾数据集，含55张雾图像与对应的Ground Truth。CVPR 2019挑战赛Dense_Haze_NTIRE...
Python-DenseNet的一个PyTorch实现
08-11
DenseNet的一个PyTorch实现
tensorflow的ckpt文件转pb模型文件
10-28
使用这个python程序可以直接将ckpt文件转成固化的模型文件，用于预测结果，注意修改路径
Python_第五篇 Keras(1)_网络 Dense层的堆叠
Blog of Mary Sun
04-22 4361
定义模型 一、激活函数 activation model=models.Sequential() model.add(layers.Dense(隐藏层个数，activation=‘’)) 1、softmax 2、softplus 3、softsign 4、relu 5、tanh 6、sigmoid 7、hard_sigmoid 8、linear 编译模型必选两个参数：优化器 optimize...
时间序列分析 | Python实现时间序列预测（LR、Dense、CNN、LSTM）
前程算法屋的博客
02-01 1424
时间序列分析 | Python实现时间序列预测（LR、Dense、CNN、LSTM）
【Python-Keras】keras.layers.Dense层的解析与使用
热门推荐
BetterBench的博客
01-05 2万+
1 Dense解析 keras.layers.Dense(units, activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None) 实现
人工神经网络（ANN）相关介绍
哈哈的博客
10-21 1705
通过使用具体的例子来实现ANN,充分了解了人工神经网络相关历史，发展，以及演变的网络；后面会继续更深入地研究相关算法！😄😄
python学习笔记_day01
Dense_forest的博客
07-15 467
1.基础语法 中文编码 Python中默认的编码格式是 ASCII 格式，在没修改编码格式时无法正确打印汉字，所以在读取中文时会报错。 #!/usr/bin/python print ("你好，世界") 以上程序执行输出结果为： File "test.py", line 2 SyntaxError: Non-ASCII character '\xe4' in file test.py on line 2, but no encoding declared; see http://www.pyth
InternalError (see above for traceback): Blas GEMM launch failed : a.shape=(x, x), b.shape=(x,x)錯誤
keineahnung2345的博客
11-27 7557
這個錯誤是在一開始訓練Keras（使用TensorFlow當backend）模型的時候就出現。Python版本：3.5.2 Keras版本：2.1.2 TensorFlow版本：1.3.0 使用`nvidia-smi`查看GPU memory的使用情況：發現己被其它程序佔滿。 試著將這些程序關掉，然後再重新運行剛剛那段代碼（不必重啟kernel），問題即可成功解決！
Dense layer
07-25
Dense层，也被称为全连接层（Fully Connected Layer），是在深度学习神经网络中常见的一个组件。它接收前一层（通常是卷积层等）输出的特征映射，并将它们转化为更适用于分类任务或者其他下游任务的形式。 ### Dense 层的工作原理： 在Dense层中，每个节点（或称为神经元）都与前一层的所有节点相连，这意味着每一层中的节点都会对输入的每一个维度进行加权求和，然后应用激活函数（如ReLU、sigmoid或tanh等）得到输出。这种结构允许模型捕捉复杂的非线性关系。 ### Dense 层的特点： 1. **连接性**：Dense层的每一层的节点都直接与上一层所有节点相联接，这使得信息可以充分地在网络内部流动。 2. **非线性处理**：通过在每个节点应用激活函数，Dense层能够处理非线性的数据分布，并帮助模型学习到复杂模式。 3. **灵活性**：Dense层可以在任意深度的网络架构中加入，用于增加模型的表达能力。 4. **权重共享**：虽然理论上每个节点都有独立的权重值，但在实际操作中，这些权重会通过反向传播算法在整个网络中共同优化。 ### 使用Dense层的例子： 在构建图像分类模型时，最后的几层往往包括密集连接层，用于从特征图中提取最终的决策。例如，在构建一个基于卷积神经网络（CNN）的图片识别系统中，最后一层通常是一个全连接层，负责将所有先前层次的特征汇聚起来，形成最终的分类结果。 ### 注意事项： - **过拟合风险**：Dense层可能导致过拟合，尤其是当网络层数过多或训练集较小的时候。为了降低过拟合的风险，常用的技术包括正则化、dropout以及更多的数据增强策略。 - **计算成本**：由于每个节点都与其他所有节点连接，因此Dense层的计算量相对较大，特别是在有大量隐藏节点的情况下。 - **初始化和梯度消失/爆炸**：需要恰当的权重初始化策略，并监控梯度变化，以避免梯度消失或爆炸问题。 总之，Dense层是构建深度学习模型的关键组件之一，对于提高模型的性能至关重要。然而，也需要谨慎设计其参数，以避免潜在的问题，如过拟合和计算效率低下。
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
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、付费专栏及课程。

余额充值