最新 | 最热门 | 最高评价

+0  LinearSVC versus SVC in scikit-learn

Tag: machine learning | scikit-learn
Robin Dong 发于 2019年01月26日 11:32 | 点击: 333 | 展开摘要
In competition ‘Quora Insincere Questions Classification’, I want to use simple TF-IDF statistics as a baseline.

def grid_search(classifier, parameters, X, y, X_train, y_train, X_test, y_test, name = 'SVC'):
begin = time.ti

查看全文: http://www.udpwork.com/item/17299.html

+0  Mac释放purgable空间

Tag: MacOSX
ideawu 发于 2019年01月18日 14:49 | 点击: 476 | 展开摘要
# sudo tmutil listlocalsnapshots /

com.apple.TimeMachine.2019-01-17-191904

com.apple.TimeMachine.2019-01-18-134752

com.apple.TimeMachine.2019-01-18-141455

com.apple.TimeMachine.2019-01-18-143636

# tmutil deletelocalsnapshots 2019-01-18

查看全文: http://www.udpwork.com/item/17291.html

+0  Some errors in dataset pipeline of Tensorflow

Tag: machine learning | numpy | tensorflow
Robin Dong 发于 2019年01月04日 15:13 | 点击: 289 | 展开摘要
To extend image datasets by using mixup,I use this snippet to mix two images:

major_image = cv2.imread('1.jpeg')
minor_image = cv2.imread('2.jpeg')
new_image = major_image * 0.9 + minor_image * 0.1
But after generating images by using this

查看全文: http://www.udpwork.com/item/17271.html

+0  在macOS下安装aria2并自动启动RPC

Tag: common | homebrew | macOS
Volcano 发于 2019年01月02日 13:41 | 点击: 411 | 展开摘要
什么是Aria2? Aria2 is a lightweight download software with Multi-Connection support. Besides HTTP(s) and FTP, it also supports BitTorrent and Metalink. 安装Aria2 最简单的方法是采用homebrew安装aria2 brew install aria2 配置RPC自启动 新增文件并编辑 /usr/local/opt/aria2/h

查看全文: http://www.udpwork.com/item/17263.html

+0  Compare implementation of tf.AdamOptimizer to its paper

Tag: machine learning | Adam | tensorflow
Robin Dong 发于 2018年11月16日 16:01 | 点击: 488 | 展开摘要
When I reviewed the implementation of Adam optimizer in tensorflow yesterday, I noticed that it’s code is different from the formulas that I saw in Adam’s paper. In tensorflow’s formulas for Adam are:

But the algorithm in

查看全文: http://www.udpwork.com/item/17201.html

+0  The bug about using hooks and MirroredStrategy in tf.estimator.Estimator

Tag: machine learning | tensorflow
Robin Dong 发于 2018年11月09日 14:25 | 点击: 567 | 展开摘要
When I was using MirroedStrategy in my tf.estimator.Estimator:

distribution = tf.contrib.distribute.MirroredStrategy(
["/device:GPU:0", "/device:GPU:1"])
config = tf.estimator.RunConfig(train_distribute=distributi

查看全文: http://www.udpwork.com/item/17194.html

+0  Some lessons from Kaggle’s competition

Tag: machine learning | Kaggle | Object Detection
Robin Dong 发于 2018年11月02日 13:23 | 点击: 557 | 展开摘要
About two months ago, I joined the competition of ‘RSNA Pneumonia Detection’ in Kaggle. It’s ended yesterday, but I still have many experiences and lessons to be rethinking.

1. Augmentation is extremely crucial. After usi

查看全文: http://www.udpwork.com/item/17180.html

+0  How Tensorflow set device for each Operation ?

Tag: machine learning | tensorflow
Robin Dong 发于 2018年10月12日 11:41 | 点击: 574 | 展开摘要
In Tensorflow, we only need to use snippet below to assign a device to a Operation:

with tf.device('/GPU:0'):
...
result = tf.matmul(a, b)
How dose it implement? Let’s take a look.

There is a mechanism called ‘context mana

查看全文: http://www.udpwork.com/item/17128.html

+0  Some tips about using google’s TPU (Cont.)

Tag: machine learning | tensorflow | TPU
Robin Dong 发于 2018年09月28日 16:23 | 点击: 898 | 展开摘要
Sometimes I get this error from TPUEstimator:

...
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 900, in run
run_metadata_ptr)

查看全文: http://www.udpwork.com/item/17110.html

+0  Some tips about using google’s TPU

Tag: machine learning | tensorflow | TPU
Robin Dong 发于 2018年09月21日 16:22 | 点击: 780 | 展开摘要
About one month ago, I submit a request to Google Research Cloud for using TPU for free. Fortunately, I received the approvement yesterday. The approvement let me use 5 regular Cloud TPUs and 100 preemptible Cloud TPUs for free for 30 days

查看全文: http://www.udpwork.com/item/17097.html

+0  Some modifications about SSD-Tensorflow

Tag: machine learning | tensorflow
Robin Dong 发于 2018年09月13日 10:54 | 点击: 755 | 展开摘要
In the previous article, I introduced a new library for Object Detection. But yesterday, after I added slim.batch_norm() into ‘nets/ssd_vgg_512.py’ like this:

def ssd_arg_scope(weight_decay=0.0005, data_format='NHWC', is_traini

查看全文: http://www.udpwork.com/item/17088.html

+0  Choosing a Object Detection Framework written by Tensorflow

Tag: machine learning | Object Detection | tensorflow
Robin Dong 发于 2018年09月07日 15:23 | 点击: 611 | 展开摘要
Recently I need to train a DNN model for object detection task. In the past, I am using the object detection framework from tensorflows’s subject — models. But there are two reasons that I couldn’t use it to do my own proj

查看全文: http://www.udpwork.com/item/17081.html
|<<<1234567>>>| 一共22页, 261条记录