Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @VahidK
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @VahidK
-
A practical lesson I learned from doing research in deep learning is to spend considerable amount of time at the beginning of the process on optimizing data loading and common operations making sure 100% of my GPU resources are utilized. It pays off massively in the long run.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I made a small package which allows reading tfrecord files in PyTorch with no tf dependency:https://github.com/vahidk/tfrecord
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
One way I made myself more productive is to write down everything I want to achieve in the foreseeable future. More recently I started also logging what I actually did and unexpected problems that I had to solve. This has helped me better plan and save time.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
One major feature I miss from TensorFlow in PyTorch is GPU-based preprocessing operations through tf.image and tf.contrib/tf.contrib.image. Pre-processing in TF can be done very efficiently on GPU. DALI is ok, but doesn't provide the same level of flexibility.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I was working on optimizing some Pytorch code today and was amazed how fast Pytorch ran a pretty non-optimal code. So I made some test cases to compare with TensorFlow. Pytorch handily beat TensorFlow running vectorized and non-vectorized code in my test cases. Here's one:pic.twitter.com/gf8FcA8vMQ
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Python is so inefficient, Python coders think twice before implementing any new algorithm; they prefer a ready made library (usually written in C++). Paradoxically this has made Python coders much more productive. C++ coders are still writing their own string classes in 2019.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We relabeled our test set with more accurate labels and found many of the models we dropped before were actually working better than the models we thought were best. Makes me wonder what percentage of published results are plain wrong because of systematic errors in evaluation.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"consider the problem is a self-driving car. In this case there is a very long tail of traffic situations that are very rare and therefore do not show up in your dataset. In this case a purely data-driven method that does not try to model the world is doomed."https://twitter.com/wellingmax/status/1119621032837636096 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Since I left Alphabet, I came to realize that computational resources can be limited! Gone are the days of using hundreds of TPUs without anyone raising an eyebrow. Now I spend a lot of time optimizing neural nets to train and run faster. The experience has been very rewarding.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
TensorFlow tip: Always use http://tf.data.experimental.map _and_batch instead of separate map and batch. I got a 1.7x improvement in reading throughput just by doing that. Another important thing is to make as many of your preprocessing ops as possible in batch and move to GPU.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I think if math was taught like this in high schools we would have many more scientists in the world. What an amazing work.https://twitter.com/3blue1brown/status/1112377677493596161 …
1:00Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is a neat tool to learn new languages.https://twitter.com/papa_fire/status/1111994073609633792 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
While TensorFlow 2 is more approachable and looks just like Python, it can have surprising behaviors at times if you aren't familiar with its symbolic API. One example with tf.while_loop and variable shape tensors was discussed in the guide.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I just started working on Effective TensorFlow 2.0 today. Ported six of the items: https://github.com/vahidk/EffectiveTensorflow/tree/v2 …. More to come.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I believe we will build AGI at some point, and by that I mean the kind of ML model that can emulate human brain, but we are no where near that. Pitching AGI to investors now, is like pitching "Uber on Pluto, for aliens". Is it theoretically possible? Yes. Is it feasible? no.https://twitter.com/OpenAI/status/1105137369408188416 …
0:06Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Swift for TensorFlow is exciting. You get a modern and efficient programming language + built-in language support for automatic differentiation + library support for massively parallel computation on GPUs/TPUs. I'm looking forward to say goodbye to Python soon!https://twitter.com/clattner_llvm/status/1103540349358694401 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My paper on real-time face landmark estimation (used by Snapchat and several other companies) just passed 1000 citations according to Google scholar. Quite a milestone! https://scholar.google.com/scholar?cluster=757491702050841438 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I wonder how many millions of hours of engineering time would have been saved, if C++ had a built-in standard linear algebra library like Eigen.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
IMO one of the most poorly designed parts of TensorFlow is tf.estimator API. I have wasted hours and days trying to hack tf.estimator to do what I want, in the hindsight I should have avoided it altogether in the first place. I hope to see a functional high-level API in tf 2.0.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Big gains in ML projects are often obtained by understanding the data not randomly trying out things. Visualize predictions/loss on both training/test data. Find/fix problems. Bonus tip: triple check your preprocessing code.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.