TRT: Support set dynamic range in int8 mode.#17524
Merged
NHZlX merged 7 commits intoPaddlePaddle:developfrom May 25, 2019
Merged
TRT: Support set dynamic range in int8 mode.#17524NHZlX merged 7 commits intoPaddlePaddle:developfrom
NHZlX merged 7 commits intoPaddlePaddle:developfrom
Conversation
trt int8 predict init op converter
enhance quant dequant fuse pass enhance op converter, trt engine, trt engine op, trt subgraph pass.
test=develop
… feature/align_fluid_quant_trt_int8
test=develop
NHZlX
force-pushed
the
feature/align_fluid_quant_trt_int8
branch
3 times, most recently
from
52d088c to
4b2366f
Compare
fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter test=develop
NHZlX
force-pushed
the
feature/align_fluid_quant_trt_int8
branch
from
4b2366f to
0475ecb
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Align fluid int8 training and trt int8 inference .
We first do this on resnet50 model and alignment is made on accuracy and speed.
Env: p4 card
Dataset: imagenet