* Pip: Move from tensorflow-gpu to tensorflow package
Since tensorflow 2.1 the regular tensorflow package contains GPU support and replaces the tensorflow-gpu package, which will be depreceated at some point.
* Readme: Update Tensorflow version
* Update Pipfile.lock
Co-authored-by: Willem Melching <willem.melching@gmail.com>
* Create workflow to update the Pipfile.lock weekly
* Update-pipfile: Also install wheel
* Install wheel in different step
* Pipfile: Only lock major versions
Assumes Semantic Versioning, and only sets the major versions of all packages
* Run update-pipfile on changes in pipfile and use tensorflow
Move from tensorflow-gpu to tensorflow, an excelent test for this PR
* [create-pull-request] automated change
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* hyundai fw query
* Change query
* this works
* That is not engine
* hyundai fw query
* Change query
* this works
* That is not engine
* Skip FW query in test_car_models
* Those routes don't fingerprint properly after speedup
* only send toyota queries to subaddresses
Co-authored-by: openpilot laptop <laptop@comma.ai>
* don't compile in docker build stage
* disable that for now
* do we need that?
* upload artifact already compresses
* that wasn't faster
This reverts commit 2221e13c71.
* try that
* don't think that's used
* this too
* check this
* less layers
* that's not in the dockerfile anymore
* system
* even less layers and clear pipenv cache
* no inline comment i guess
* uninstall pipenv after we're done with it
* separate build job adds too much overhead
* quotes
* clean that up
* increase timeout
* cleanup
* bigmodel
* more debug print
* debugging bigmodel
* remove the tanh, debugging
* print images/buffers
* disassemble the command queues
* decompiler
* dump the shaders
* full disasm
* support patching kernel and fixing convolution_horizontal_reduced_reads_1x1
* microbenchmark
* 42 GFLOPS, 1 GB/s
* gemm benchmark
* 75 GFLOPS vs 42 GFLOPS
* 115 GFLOPS
* oops, never mind
* gemm image is slow
* this is pretty hopeless
* gemm image gets 62 GFLOPS
* this is addictive and still a waste of time
* cleanup cleanup
* that hook was dumb
* tabbing
* more tabbing
Co-authored-by: Comma Device <device@comma.ai>
* way cleaner take 2
* cleanup
* be more relaxed
* just let it be
* don't drive backwards or upside down
* do this more
* vNED sometyimes invalid
* use reasonble stds
* stability in nonlinear zone
* previous metrics were without publishing
Remove panda / giraffe mention in footnotes where possible
Car harnesses now available, removed subscript for known HKG models; left subscript for not known models
openpilot laptop
Ewout ter Hoeven
Willem Melching
TK211X
Adeeb Shihadeh
Adeeb
VirtuallyChris
Harald Schafer
George Hotz
Hylke Jellema
eFini
Comma Device
Erich Moraga
Noel Schenk
Andre Volmensky
Chris Souers