মিডিয়া
- টুইট
- টুইট এবং উত্তর
- মিডিয়া, বর্তমান পৃষ্ঠা।
-
Google's TPUs are now available in Cloud ML Engine. Swap Estimator for TPUEstimator and use --scale-tier=BASIC_TPU and you are up and training on a TPU. Step by step docs here: https://cloud.google.com/ml-engine/docs/tensorflow/using-tpus …pic.twitter.com/Lc7X95JnX5
এই থ্রেডটি দেখান -
12/ And now the really cool part. Here is my model paused during training in a vanilla Python debugger: the values of weights, biases, activations, you name it are now visible. Yay! Eager rocks!pic.twitter.com/LiSTVwCvGy
এই থ্রেডটি দেখান -
10/ Also, tfe.GradientTape for differentiating any piece of code against any set of variables. Handy if you do not want to wrap your loss into a function and know the list of trainable variables explicitly, as in Keras Models where the list is in model.variables.pic.twitter.com/zs7sXgyrDC
এই থ্রেডটি দেখান -
9/ For power-users, there are alternative functions for computing gradients in eager mode: implicit_value_and_gradients gets the value of the loss at the same time as gradients. The code above can be made slightly more efficient:pic.twitter.com/q2eUvBzQWJ
এই থ্রেডটি দেখান -
8/ To pipe data into your training loop, my_next_batch() can be implemented with vanilla Python or use the http://tf.data .Dataset API which allows training on out of memory datasets. In eager mode, it is very natural to use:pic.twitter.com/ygggQGjizG
এই থ্রেডটি দেখান -
7/ And finally the training loop. You are passing your model as a parameter to grads so it is pretty obvious what weights and biases are being modified by the training.pic.twitter.com/l2aoPOWFhF
এই থ্রেডটি দেখান -
-
5/ Tensorflow eager knows how to compute the gradient for this loss, relatively to the implicit weights and biases of your layers. "grads" is now a function of the same parameters as your loss function.pic.twitter.com/134PBH43d9
এই থ্রেডটি দেখান -
4/ You need a loss function, comparing what your model makes of the features against a target answer "yt"pic.twitter.com/zqMLv31SLx
এই থ্রেডটি দেখান -
3/ In Eager mode, you know where your weights are because you have to put them somewhere yourself. My preferred pattern: a basic class. Define your layers in the constructor, line them up according to your preferred architecture in a "predict" function.pic.twitter.com/zhh3qsMraS
এই থ্রেডটি দেখান -
1/ Tensorflow eager mode in 12 tweets. You are going to love tweet #12
To begin, import and enable eager mode:pic.twitter.com/5UloE69nEp
এই থ্রেডটি দেখান -
And here is the code: https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd …pic.twitter.com/6KGMAI3mtV
এই থ্রেডটি দেখান -
From playing pong to creating neural networks that can architect neural networks: "
#Tensorflow and deep reinforcement learning, without a PhD". The#io2018 recording is out:https://youtu.be/t1A3NTttvBAএই থ্রেডটি দেখান -
A new runtime on AppEngine: node.js Serverless, autoscaled, fully managed, and built on state of the art open source container on bare metal tech: gvisor https://github.com/google/gvisor pic.twitter.com/b7tHWsxZMz
এই থ্রেডটি দেখান -
Progress in unsupervised learning. This is cool. And NOT supervised. Just forcing the reconstructed 3D to "make sense".
#IO2018pic.twitter.com/K8anK1DPK1
-
The code from today's
#IO2018 reinforcement learning session is now available on GitHub, along with all the other "Tensorflow without a PhD" stuff (code, slides, videos) in this new repo: https://github.com/GoogleCloudPlatform/tensorflow-without-a-phd … There is a trained PONG checkpoint too
pic.twitter.com/crgGhnDNO9
-
Why is the humble game of PONG being demoed at Google I/O ? Answer here: "TensorFlow and deep reinforcement learning, without a PhD" https://events.google.com/io/schedule/?sid=af46615a-6bb3-4f20-be14-b715bec5809c … on May 10.
#io18#reinforcementlearning Pong and beyond!pic.twitter.com/v2vPQiPEsH
-
New hands-on lab at
@QConAI next Monday with@texasmichelle: learn how to whip a neural network into shape and explore the secrets of data sequences and RNNs: https://qcon.ai/qconai2018/workshop/tensorflow-without-phd-deep-learning-guided-codelabs … . ML learners welcome. No PhD required.pic.twitter.com/WwV8oKglhx
-
"Modern RNN architectures" is coming to
#ainextcon Santa Clara on Thursday next week, with a new hand-on lab on RNNs on Wednesday. Come and learn machine learninig!#chall2learnai at http://aisv18.xnextcon.com/ pic.twitter.com/YQw8y6PIcr
-
right here: RNN basics (Shakespeare): https://youtu.be/fTUwdXUFfI8 Modern RNNs (toxicity detector, translate):https://youtu.be/pzOzmxCR37I
লোড হতে বেশ কিছুক্ষণ সময় নিচ্ছে।
টুইটার তার ক্ষমতার বাইরে চলে গেছে বা কোনো সাময়িক সমস্যার সম্মুখীন হয়েছে আবার চেষ্টা করুন বা আরও তথ্যের জন্য টুইটারের স্থিতি দেখুন।