+0  Some tips about Python, Pandas, and Tensorflow

Tag: develope | pandas | tensorflow
Robin Dong 发于 2019年02月06日 10:47 | 点击: 3419 | 展开摘要
There are some useful tips for using Keras and Tensorflow to build models.

1. Using applications.inception_v3.InceptionV3(include_top = False, weights = ‘Imagenet’) to get pretrained parameters for InceptionV3 model, the consol

查看全文: http://www.fwnace.com/item/17377.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: 916 | 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.fwnace.com/item/17271.html

+0  Books I read in year 2018

Tag: life | Arduino | sklearn | tensorflow
Robin Dong 发于 2018年12月20日 12:02 | 点击: 1113 | 展开摘要
In the 2018 year, I continued to learn more knowledge about machine learning and deep Learning. “Deep Learning” is pretty suitable for me and “Hands-On Machine Learning with Scikit-Learn and TensorFlow” is also a won

查看全文: http://www.fwnace.com/item/17245.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: 1022 | 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.fwnace.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: 1201 | 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.fwnace.com/item/17194.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: 1075 | 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.fwnace.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: 1478 | 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

查看全文: http://www.fwnace.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: 1392 | 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.fwnace.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: 1350 | 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.fwnace.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: 1134 | 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.fwnace.com/item/17081.html

+0  Do tf.random_crop() operation on GPU

Tag: machine learning | tensorflow
Robin Dong 发于 2018年07月27日 15:12 | 点击: 754 | 展开摘要
When I run code like:

with tf.device('/GPU:0'):
images = tf.random_crop(images, [IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNELS])
it reports:

Could not satisfy explicit device specification '/device:GPU:0' because no supported kernel for

查看全文: http://www.fwnace.com/item/17017.html

+0  Regularization loss in ‘slim’ library of Tensorflow

Tag: machine learning | tensorflow
Robin Dong 发于 2018年07月19日 15:16 | 点击: 857 | 展开摘要
My python code using slim library to train classification model in Tensorflow:

with tf.contrib.slim.arg_scope(mobilenet_v2.training_scope(weight_decay = 0.001)):
logits, _ = mobilenet_v2.mobilenet(images, NUM_CLASSES)


查看全文: http://www.fwnace.com/item/17018.html
|<<<12>>>| 一共2页, 15条记录