Can we compress the knowledge of a large dataset into a small number of synthetically generated images? Researchers at FAIR, MIT, and Berkeley investigate in their paper: https://bit.ly/2GvWnAy
🙏Thanks to: @vahidreza01
🙏Thanks to: @vahidreza01
#InstaGAN Excels in Instance-Aware Image-To-Image Translation
https://medium.com/syncedreview/instagan-excels-in-instance-aware-image-to-image-translation-64fb7d0344ae
https://medium.com/syncedreview/instagan-excels-in-instance-aware-image-to-image-translation-64fb7d0344ae
#مقاله
یک کار جدید Image to image Translation
https://t.iss.one/cvision/892
مقاله:
https://arxiv.org/pdf/1812.10889.pdf
کد:
https://github.com/sangwoomo/instagan
The paper #InstaGAN: Instance-Aware Image-to-Image Translation has been accepted by the respected International Conference on Learning Representations (#ICLR) 2019, which will take place this May in New Orleans, USA.
This new research is based on #CycleGAN, a GAN variant which can learn to translate images without paired training data to overcome the limitations of one-by-one pairing of #pix2pix in image translation. CycleGAN can automatically translate two given unordered image sets X and Y, but it cannot encode instance information in an image. CycleGAN results however are not ideal when translating images involving specific features of the target. The InstaGAN system overcomes this problem and combines instance information from multiple task targets.
کارها و مطالب مشابه و مرتبط:
https://t.iss.one/cvision/214
https://t.iss.one/cvision/870
https-://t.iss.one/cvision/863
#Image_to_Image_Translation #GAN
یک کار جدید Image to image Translation
https://t.iss.one/cvision/892
مقاله:
https://arxiv.org/pdf/1812.10889.pdf
کد:
https://github.com/sangwoomo/instagan
The paper #InstaGAN: Instance-Aware Image-to-Image Translation has been accepted by the respected International Conference on Learning Representations (#ICLR) 2019, which will take place this May in New Orleans, USA.
This new research is based on #CycleGAN, a GAN variant which can learn to translate images without paired training data to overcome the limitations of one-by-one pairing of #pix2pix in image translation. CycleGAN can automatically translate two given unordered image sets X and Y, but it cannot encode instance information in an image. CycleGAN results however are not ideal when translating images involving specific features of the target. The InstaGAN system overcomes this problem and combines instance information from multiple task targets.
کارها و مطالب مشابه و مرتبط:
https://t.iss.one/cvision/214
https://t.iss.one/cvision/870
https-://t.iss.one/cvision/863
#Image_to_Image_Translation #GAN
Telegram
Tensorflow
#InstaGAN Excels in Instance-Aware Image-To-Image Translation
https://medium.com/syncedreview/instagan-excels-in-instance-aware-image-to-image-translation-64fb7d0344ae
https://medium.com/syncedreview/instagan-excels-in-instance-aware-image-to-image-translation-64fb7d0344ae
#سورس_کد
#InstaGAN
این مقاله نقص های cycleGan را رفع کرده.
#PyTorch implementation of "InstaGAN: Instance-aware Image Translation" (ICLR 2019)
code:
https://github.com/sangwoomo/instagan
paper:
https://arxiv.org/pdf/1812.10889.pdf
blog post:
https://t.iss.one/cvision/892
بیشتر:
https://t.iss.one/cvision/893
#Image_to_Image_Translation #GAN
#InstaGAN
این مقاله نقص های cycleGan را رفع کرده.
#PyTorch implementation of "InstaGAN: Instance-aware Image Translation" (ICLR 2019)
code:
https://github.com/sangwoomo/instagan
paper:
https://arxiv.org/pdf/1812.10889.pdf
blog post:
https://t.iss.one/cvision/892
بیشتر:
https://t.iss.one/cvision/893
#Image_to_Image_Translation #GAN
سری توئیت های اندرونگ
1/The rise of Software Engineering required inventing processes like version control, code review, agile, to help teams work effectively. The rise of AI & Machine Learning Engineering is now requiring new processes, like how we split train/dev/test, model zoos, etc.
2/I'm also seeing many AI teams use new processes that haven't been formalized or named yet, ranging from how we write product requirement docs to how we version data and ML pipelines. This is an exciting time for developing these ideas!
3/Have you seen an idea for organizing ML projects that you'd like to share with others? If so please reply to this tweet!
https://twitter.com/AndrewYNg/status/1080886439380869122
1/The rise of Software Engineering required inventing processes like version control, code review, agile, to help teams work effectively. The rise of AI & Machine Learning Engineering is now requiring new processes, like how we split train/dev/test, model zoos, etc.
2/I'm also seeing many AI teams use new processes that haven't been formalized or named yet, ranging from how we write product requirement docs to how we version data and ML pipelines. This is an exciting time for developing these ideas!
3/Have you seen an idea for organizing ML projects that you'd like to share with others? If so please reply to this tweet!
https://twitter.com/AndrewYNg/status/1080886439380869122
Twitter
Andrew Ng
1/The rise of Software Engineering required inventing processes like version control, code review, agile, to help teams work effectively. The rise of AI & Machine Learning Engineering is now requiring new processes, like how we split train/dev/test, model…
This media is not supported in your browser
VIEW IN TELEGRAM
#سورس_کد
Keras implementation of Sketch RNN
https://github.com/eyalzk/sketch_rnn_keras
#keras #Seq2SeqVAE #LSTM
Keras implementation of Sketch RNN
https://github.com/eyalzk/sketch_rnn_keras
#keras #Seq2SeqVAE #LSTM
#آموزش استفاده از TPU گوگل کولب و خواندن و پردازش داده های تصویری با tf.data dataset تنسرفلو
Here is an end-to-end canonical sample for training a model on Cloud TPUs in Keras. It has full code for loading the data from scratch using tf.data .Dataset and also exporting the trained model to ML Engine for inference.
Colab notebook:
https://colab.research.google.com/github/GoogleCloudPlatform/training-data-analyst/blob/master/courses/fast-and-lean-data-science/01_MNIST_TPU_Keras.ipynb
#TPU #keras #colab
Here is an end-to-end canonical sample for training a model on Cloud TPUs in Keras. It has full code for loading the data from scratch using tf.data .Dataset and also exporting the trained model to ML Engine for inference.
Colab notebook:
https://colab.research.google.com/github/GoogleCloudPlatform/training-data-analyst/blob/master/courses/fast-and-lean-data-science/01_MNIST_TPU_Keras.ipynb
#TPU #keras #colab
#سورس_کد
#Mozilla has released open source #speech recognition model & data. Word error rate 6.5%, which is close to human.
Project DeepSpeech is an open source Speech-To-Text engine, using a model trained by machine learning techniques, based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow project to make the implementation easier.
Data: https://voice.mozilla.org/data
400k recordings, 500 hours of speech.
Model: https://github.com/mozilla/DeepSpeech
TensorFlow implementation of Baidu's DeepSpeech architecture.
https://deepspeech.readthedocs.io/en/latest/
DeepSpeech’s code documentation!
مرتبط با:
https://t.iss.one/cvision/875
https://t.iss.one/cvision/850
#speech_recognition #Tensorflow
#Mozilla has released open source #speech recognition model & data. Word error rate 6.5%, which is close to human.
Project DeepSpeech is an open source Speech-To-Text engine, using a model trained by machine learning techniques, based on Baidu's Deep Speech research paper. Project DeepSpeech uses Google's TensorFlow project to make the implementation easier.
Data: https://voice.mozilla.org/data
400k recordings, 500 hours of speech.
Model: https://github.com/mozilla/DeepSpeech
TensorFlow implementation of Baidu's DeepSpeech architecture.
https://deepspeech.readthedocs.io/en/latest/
DeepSpeech’s code documentation!
مرتبط با:
https://t.iss.one/cvision/875
https://t.iss.one/cvision/850
#speech_recognition #Tensorflow
👍1
#آموزش
Entity Embeddings For Categorical Data in Keras
فرض کنید داده های ساختاریافته را میخواهید به کراس بدهید. برای متغیرهای categorical چه میکنید؟ احتمالا آنها را one-hot میکنید. مثلا برای روزهای هفته یک بردار به طول 7 که یکی از خانه های آن یک و بقیه 0 است!
اما راهی که خیلی وقت ها ما را به جواب بهتر میرساند استفاده از لایه embedding برای کد کردن روزهای هفته مثلا در یک وکتور به طول سه dense خواهد بود.
جزئیات پیاده سازی این کار در Keras و توضیحات را میتوانید بخوانید:
https://github.com/mayanksatnalika/ipython/tree/master/embeddings%20project
https://medium.com/@satnalikamayank12/on-learning-embeddings-for-categorical-data-using-keras-165ff2773fc9
#keras #embedding #categorical
Entity Embeddings For Categorical Data in Keras
فرض کنید داده های ساختاریافته را میخواهید به کراس بدهید. برای متغیرهای categorical چه میکنید؟ احتمالا آنها را one-hot میکنید. مثلا برای روزهای هفته یک بردار به طول 7 که یکی از خانه های آن یک و بقیه 0 است!
اما راهی که خیلی وقت ها ما را به جواب بهتر میرساند استفاده از لایه embedding برای کد کردن روزهای هفته مثلا در یک وکتور به طول سه dense خواهد بود.
جزئیات پیاده سازی این کار در Keras و توضیحات را میتوانید بخوانید:
https://github.com/mayanksatnalika/ipython/tree/master/embeddings%20project
https://medium.com/@satnalikamayank12/on-learning-embeddings-for-categorical-data-using-keras-165ff2773fc9
#keras #embedding #categorical
GitHub
mayanksatnalika/ipython
ipython notebooks for machine learning, code behind work at the blog - mayanksatnalika/ipython
The 25 Best Data Science and Machine Learning GitHub Repositories from 2018
https://www.analyticsvidhya.com/blog/2018/12/best-data-science-machine-learning-projects-github/
https://www.analyticsvidhya.com/blog/2018/12/best-data-science-machine-learning-projects-github/
Analytics Vidhya
The 25 Best Data Science and Machine Learning GitHub Repositories from 2018
List of 25 best machine learning and data science github repositories from 2018 with projects divided into different categories.
#خبر
گیت هاب کراس تعداد star های بیشتری نسبت به بیت کوین دارد! جالبه...
https://twitter.com/fchollet/status/1081563386536738816
#keras #github
گیت هاب کراس تعداد star های بیشتری نسبت به بیت کوین دارد! جالبه...
https://twitter.com/fchollet/status/1081563386536738816
#keras #github
#خبر
آموزش و تست کلسیفایر CNN با 1000fps با استفاده از LUTهای FPGA روی MNIST.
https://ryuz.txt-nifty.com/blog/2019/01/lut-network-cnn.html
https://github.com/ryuz/BinaryBrain
#fpga
آموزش و تست کلسیفایر CNN با 1000fps با استفاده از LUTهای FPGA روی MNIST.
https://ryuz.txt-nifty.com/blog/2019/01/lut-network-cnn.html
https://github.com/ryuz/BinaryBrain
#fpga
Ryuzのブログ
LUT-Network CNN実機動作 - Ryuzのブログ
概要 Zybo Z7-20 にて、LUT-Network で構成したCNNが1000fpsの高速度カメラ入力にてリアルタイムで動き始めたので、結果を纏めておきます。 システムの構成とか、カメラやOLEDの高速駆動とかは過去記事をご参照ください。 RTLの生成に利用したコードは、githubに置いております。 畳み込み(CNN)が動き出したことによって、実際に組め...
#آموزش #بلاگ_پست_فارسی
Connectionist Temporal Classification – CTC
https://blog.class.vision/1397/10/connectionist-temporal-classificationctc/
#ctc
Connectionist Temporal Classification – CTC
https://blog.class.vision/1397/10/connectionist-temporal-classificationctc/
#ctc
آمار ناراحت کننده بازگشت مهاجران تحصیلات تکمیلی امریکا به نقل از NSF
ایران بیشترین نرخ عدم بازگشت مهاجرات علمی تحصیلی به آمریکا را دارد.
منبع گزارش:
https://www.nsf.gov/statistics/2017/nsf17306/static/report/nsf17306.pdf
🙏Thanks to: @Sepehr_Qooja
ایران بیشترین نرخ عدم بازگشت مهاجرات علمی تحصیلی به آمریکا را دارد.
منبع گزارش:
https://www.nsf.gov/statistics/2017/nsf17306/static/report/nsf17306.pdf
🙏Thanks to: @Sepehr_Qooja
#منبع #کورس
MIT 6.S094: Deep Learning for Self-Driving Cars - 2019
This class is an introduction to the practice of deep learning through the applied theme of building a self-driving car. It is open to beginners and is designed for those who are new to machine learning, but it can also benefit advanced researchers in the field looking for a practical overview of deep learning methods and their application.
https://selfdrivingcars.mit.edu
🙏Thanks to: @cyberbully_gng
MIT 6.S094: Deep Learning for Self-Driving Cars - 2019
This class is an introduction to the practice of deep learning through the applied theme of building a self-driving car. It is open to beginners and is designed for those who are new to machine learning, but it can also benefit advanced researchers in the field looking for a practical overview of deep learning methods and their application.
https://selfdrivingcars.mit.edu
🙏Thanks to: @cyberbully_gng
#منبع #کورس
CS224n: Natural Language Processing with Deep Learning
#Stanford / Winter 2019
Public lecture videos: Once the course has completed, we plan to also make the videos publicly available on YouTube.
https://web.stanford.edu/class/cs224n/
This year, CS224n will be taught for the first time using PyTorch rather than TensorFlow
🙏Thanks to: @cyberbully_gng
CS224n: Natural Language Processing with Deep Learning
#Stanford / Winter 2019
Public lecture videos: Once the course has completed, we plan to also make the videos publicly available on YouTube.
https://web.stanford.edu/class/cs224n/
This year, CS224n will be taught for the first time using PyTorch rather than TensorFlow
🙏Thanks to: @cyberbully_gng
#آموزش #سورس کد
پیاده سازی یک مساله multitask-learning با تنسورفلو. در این دسته مساله ها یک شبکه برای چندین تسک مرتبط اما متفاوت آموزش میبیند و ما چندی تابع loss داریم. + کد در گوگل کولب
Multitask learning in TensorFlow with the Head API
بلاگ پست:
https://towardsdatascience.com/multitask-learning-in-tensorflow-with-the-head-api-68f2717019df
کد در کولب:
https://colab.research.google.com/drive/1NMB9lpi7P-GkkELkMU0h-yHtUq531D_Z
پیاده سازی یک مساله multitask-learning با تنسورفلو. در این دسته مساله ها یک شبکه برای چندین تسک مرتبط اما متفاوت آموزش میبیند و ما چندی تابع loss داریم. + کد در گوگل کولب
Multitask learning in TensorFlow with the Head API
بلاگ پست:
https://towardsdatascience.com/multitask-learning-in-tensorflow-with-the-head-api-68f2717019df
کد در کولب:
https://colab.research.google.com/drive/1NMB9lpi7P-GkkELkMU0h-yHtUq531D_Z
Medium
Multitask learning in TensorFlow with the Head API
A fundamental characteristic of human learning is that we learn many things simultaneously. The equivalent idea in machine learning is…
Multitask learning:
https://t.iss.one/cvision/911
https://t.iss.one/cvision/911
Forwarded from انجمن علمی دانشکده کامپیوتر
انجمن علمی دانشکده کامپیوتر برگزار میکند:
دوره آموزشی مقدماتی یادگیری عمیق با رویکرد عملی
📚مدرس : علیرضا اخوان پور
🗓 تاریخ : ۱۸ و ۲۵ بهمن ماه
⏱ مدت زمان دوره: ۱۲ ساعت
🏢 مکان : دانشگاه شهید رجایی
برای اطلاعات بیشتر و ثبت نام به لینک زیر مراجعه شود
https://cesru.ir/course/deep-learning/
ظرفیت محدود
💰تخفیف ویژه برای دانشجویان دانشگاه رجایی💰
#یادگیری_عمیق #دوره_آموزشی #انجمن_علمی_دانشکده_کامپیوتر #دانشگاه_شهید_رجایی
دوره آموزشی مقدماتی یادگیری عمیق با رویکرد عملی
📚مدرس : علیرضا اخوان پور
🗓 تاریخ : ۱۸ و ۲۵ بهمن ماه
⏱ مدت زمان دوره: ۱۲ ساعت
🏢 مکان : دانشگاه شهید رجایی
برای اطلاعات بیشتر و ثبت نام به لینک زیر مراجعه شود
https://cesru.ir/course/deep-learning/
ظرفیت محدود
💰تخفیف ویژه برای دانشجویان دانشگاه رجایی💰
#یادگیری_عمیق #دوره_آموزشی #انجمن_علمی_دانشکده_کامپیوتر #دانشگاه_شهید_رجایی