Sergei Nikolaev 4996e3aca2 TensorRT 6.0 support and PyTorch->ONNX->TRT6 unit test (#26426) ...

Summary:
This PR makes Caffe2 compatible with TensorRT 6. To make sure it works well, new unit test is added. This test checks PyTorch->ONNX->TRT6 inference flow for all classification models from TorhchVision Zoo.
Note on CMake changes: it has to be done in order to import onnx-tensorrt project. See https://github.com/pytorch/pytorch/issues/18524 for details.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/26426

Reviewed By: hl475

Differential Revision: D17495965

Pulled By: houseroad

fbshipit-source-id: 3e8dbe8943f5a28a51368fd5686c8d6e86e7f693

2019-10-25 13:01:57 -07:00

..

docs

…

examples

Adding models to jenkins benchmark script (#21010)

2019-05-30 15:17:40 -07:00

helpers

Add elementwise_affine for LayerNormGradientOp (#19982)

2019-05-03 15:33:46 -07:00

ideep

caffe2 python ideep conv_op test_int8_convolution skip for python 3

2019-10-08 21:31:11 -07:00

layers

Change dper3 loss module to match dper2 (#28265)

2019-10-18 10:08:38 -07:00

mint

…

mkl

…

modeling

Add more logging in net modifier

2019-10-21 17:53:00 -07:00

models

Adding ShufflenetV2 to caffe2's benchmark suite. (#20180)

2019-05-23 20:40:17 -07:00

onnx

Automatic update of fbcode/onnx to 23bb6ea1a71f08e200114a153f48bd7adb66d486 (#26441)

2019-09-24 05:38:52 -07:00

operator_test

change empty range tolorrance logging

2019-10-23 09:39:39 -07:00

predictor

Supporting Manifold DB in Predictor Exporter (#22334)

2019-07-01 16:17:02 -07:00

rnn

…

serialized_test

Output sequence probability with CTC beam search, optional multiple output sequences (#21927)

2019-07-02 17:29:13 -07:00

test

…

trt

TensorRT 6.0 support and PyTorch->ONNX->TRT6 unit test (#26426)

2019-10-25 13:01:57 -07:00

__init__.py

…

_import_c_extension.py

…

allcompare_test.py

…

attention.py

…

benchmark_generator.py

…

binarysize.py

…

brew_test.py

…

brew.py

…

build.py

…

cached_reader.py

Pass loop_over optional parameter for cached reader properly. (#21929)

2019-06-19 18:15:32 -07:00

caffe_translator_test.py

…

caffe_translator.py

…

checkpoint_test.py

…

checkpoint.py

Remove setting logger level in caffe2.python.checkpoint (#19803)

2019-05-10 07:00:58 -07:00

CMakeLists.txt

…

cnn.py

…

compatibility.py

…

context_test.py

…

context.py

…

control_ops_grad_test.py

Fix the weird bug in control_flow_op_test.py (#26931)

2019-09-26 20:44:03 -07:00

control_ops_grad.py

…

control_ops_util.py

…

control_test.py

…

control.py

…

convert_test.py

…

convert.py

…

convnet_benchmarks_test.py

…

convnet_benchmarks.py

…

core_gradients_test.py

Back out "Back out "[Caffe2] Fix device_option propagation"" (#25908)

2019-09-17 04:01:36 -07:00

core_test.py

…

core.py

BlobReference __getattr__ can only throw AttributeError (#26654)

2019-09-23 13:01:00 -07:00

crf_predict.py

…

crf_viterbi_test.py

…

crf.py

…

data_parallel_model_test.py

…

data_parallel_model.py

skip import nccl and gloo_gpu in cpu machine (#22522)

2019-07-10 11:56:56 -07:00

data_workers_test.py

…

data_workers.py

…

dataio_test.py

Fix for flaky caffe2 dataio test (test_time_limit_reader_with_short_limit) (#27592)

2019-10-10 13:53:58 -07:00

dataio.py

Rearrange stopping condition in CompositeReader (#20062)

2019-05-06 15:06:32 -07:00

dataset.py

…

db_file_reader.py

…

db_test.py

…

device_checker.py

…

dlpack.h

…

dyndep.py

guard dyndep with a lock (#26153)

2019-09-13 11:38:14 -07:00

embedding_generation_benchmark.py

…

experiment_util.py

…

extension_loader.py

always restore dlopen flag in dyndep (#22958)

2019-07-17 10:26:25 -07:00

filler_test.py

…

functional_test.py

…

functional.py

…

fused_8bit_rowwise_conversion_ops_test.py

…

gradient_check_test.py

…

gradient_checker.py

Adding gradient to Boolean Mask operator (#21423)

2019-06-06 20:48:47 -07:00

gru_cell.py

…

hip_test_util.py

…

hsm_util.py

…

hypothesis_test_util.py

Hypothesis tests: add ability to enforce shape inference (#23935)

2019-08-13 05:32:41 -07:00

hypothesis_test.py

Enable Unique operator tests on ROCm

2019-09-11 16:36:14 -07:00

ideep_test_util.py

…

layer_model_helper.py

Integrate FC fp16 exporter into Dper2 (#26582)

2019-09-29 10:19:28 -07:00

layer_model_instantiator.py

…

layer_parameter_sharing_test.py

Add validator for optimizers when parameters are shared

2019-04-17 21:10:38 -07:00

layer_test_util.py

…

layers_test.py

Add support for attention weight in SparseLookup (#26748)

2019-10-08 20:22:25 -07:00

lengths_reducer_fused_8bit_rowwise_ops_test.py

…

lengths_reducer_rowwise_8bit_ops_test.py

…

lstm_benchmark.py

…

memonger_test.py

…

memonger.py

Fix typo "properlyh"

2019-08-09 11:43:04 -07:00

mkl_test_util.py

…

model_device_test.py

…

model_helper_test.py

…

model_helper.py

…

modifier_context.py

…

mpi_python.cc

…

muji_test.py

…

muji.py

…

net_builder_test.py

…

net_builder.py

…

net_drawer.py

…

net_printer_test.py

…

net_printer.py

Fix spelling errors (#21665)

2019-06-13 15:21:55 -07:00

nomnigraph_test.py

…

nomnigraph_transformations_test.py

…

nomnigraph_transformations.py

…

nomnigraph.py

…

normalizer_context.py

…

normalizer_test.py

…

normalizer.py

…

numa_benchmark.py

…

numa_test.py

…

observer_test.py

…

operator_fp_exceptions_test.py

…

optimizer_context.py

…

optimizer_test_util.py

…

optimizer_test.py

…

optimizer.py

Add validator for optimizers when parameters are shared

2019-04-17 21:10:38 -07:00

parallel_workers_test.py

Add event and event_counter columns to caffe2_usage_tracer table (#21739)

2019-06-13 12:06:02 -07:00

parallel_workers.py

get rid of deprecated thread.isAlive() to use py2.6 modern form is_alive()

2019-10-22 15:37:31 -07:00

parallelize_bmuf_distributed_test.py

…

pipeline_test.py

…

pipeline.py

…

predictor_constants.py

…

pybind_state_dlpack.cc

…

pybind_state_dlpack.h

…

pybind_state_gpu.cc

add simple memory analyzer and log warning if GPU underutilized (#21024)

2019-05-28 19:58:54 -07:00

pybind_state_hip.cc

Fix get_gpu_memory_info in non-cuda builds (#21054)

2019-05-28 23:05:15 -07:00

pybind_state_ideep.cc

…

pybind_state_int8.cc

…

pybind_state_nomni.cc

…

pybind_state_registry.cc

…

pybind_state_registry.h

…

pybind_state.cc

weight_names bug fix (#23848)

2019-08-06 10:58:43 -07:00

pybind_state.h

Support unpickle py2 NetDef object in py3 (#26147)

2019-09-18 02:02:34 -07:00

python_op_test.py

…

queue_util.py

…

record_queue.py

…

recurrent.py

…

regularizer_context.py

…

regularizer_test.py

Implement "trimmed lasso" regularization and support all available regularization in a single interface (#22966)

2019-07-17 16:12:31 -07:00

regularizer.py

Initial commit for L0 norm approx (#27756)

2019-10-11 11:24:34 -07:00

rnn_cell.py

…

schema_test.py

Pass LRU hash output evicted_values to SparseLookup (#21389)

2019-07-02 11:27:37 -07:00

schema.py

Pass LRU hash output evicted_values to SparseLookup (#21389)

2019-07-02 11:27:37 -07:00

scope_test.py

…

scope.py

…

session_test.py

…

session.py

…

sparse_to_dense_mask_test.py

Increase static tolerance for negative feature ids

2019-05-20 19:09:22 -07:00

sparse_to_dense_test.py

…

task_test.py

…

task.py

…

test_util.py

…

text_file_reader.py

…

timeout_guard.py

…

toy_regression_test.py

…

transformations_test.py

…

transformations.py

…

tt_core_test.py

…

tt_core.py

…

utils_test.py

…

utils.py

Query caffe2 operator stats for detailed execution info (#20924)

2019-06-13 23:41:04 -07:00

visualize.py

…

workspace_test.py

Pass Variable into Caffe2 ops, by requiring that the Variable doesn't require grad (#22473)

2019-07-08 11:31:10 -07:00

workspace.py

Fix get_gpu_memory_info in non-cuda builds (#21054)

2019-05-28 23:05:15 -07:00