ขนาดวิดีโอ: 1280 X 720853 X 480640 X 360
แสดงแผงควบคุมโปรแกรมเล่น
เล่นอัตโนมัติ
เล่นใหม่
Todd is such a nice speaker
23:27: why is the JIT operating on the TF graph ? Shouldn't it operate on the XLA graph ??
Regarding the XLA JIT results, why there can be slow downs? Is it due to the JIT compilation time (which would count as the runtime for TF)?
Great stuff.
29:49 - What is the difference between AOT compilation and simple compilation (eg: GCC for C,C++) ?
AOT is pretty much the same as simple compilation. Here, the XLA is the compiler and the TF Computation graph (with feeds/fetches etc.) is the input program.
Why ON_1 flag works only for GPU device, but not for CPU? How to use JIT for existing .pb file on CPU?
Do feeds in tfcompile necessarily need input shapes?
How to edit xla file
how to download it?
With the help of tensorflow can we build chatbot..?
first
Todd is such a nice speaker
23:27: why is the JIT operating on the TF graph ? Shouldn't it operate on the XLA graph ??
Regarding the XLA JIT results, why there can be slow downs? Is it due to the JIT compilation time (which would count as the runtime for TF)?
Great stuff.
29:49 - What is the difference between AOT compilation and simple compilation (eg: GCC for C,C++) ?
AOT is pretty much the same as simple compilation. Here, the XLA is the compiler and the TF Computation graph (with feeds/fetches etc.) is the input program.
Why ON_1 flag works only for GPU device, but not for CPU? How to use JIT for existing .pb file on CPU?
Do feeds in tfcompile necessarily need input shapes?
How to edit xla file
how to download it?
With the help of tensorflow can we build chatbot..?
first