File to run Slow fast architecture for int 8 calibration

Slow_fast_int8.py

#
# Copyright 1993-2019 NVIDIA Corporation.  All rights reserved.
#
# NOTICE TO LICENSEE:
#
# This source code and/or documentation ("Licensed Deliverables") are
# subject to NVIDIA intellectual property rights under U.S. and
# international Copyright laws.
#
# These Licensed Deliverables contained herein is PROPRIETARY and
# CONFIDENTIAL to NVIDIA and is being provided under the terms and
# conditions of a form of NVIDIA software license agreement by and
# between NVIDIA and Licensee ("License Agreement") or electronically
# accepted by Licensee.  Notwithstanding any terms or conditions to
# the contrary in the License Agreement, reproduction or disclosure
# of the Licensed Deliverables to any third party without the express
# written consent of NVIDIA is prohibited.
#
# NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
# LICENSE AGREEMENT, NVIDIA MAKES NO REPRESENTATION ABOUT THE
# SUITABILITY OF THESE LICENSED DELIVERABLES FOR ANY PURPOSE.  IT IS
# PROVIDED "AS IS" WITHOUT EXPRESS OR IMPLIED WARRANTY OF ANY KIND.
# NVIDIA DISCLAIMS ALL WARRANTIES WITH REGARD TO THESE LICENSED
# DELIVERABLES, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY,
# NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.
# NOTWITHSTANDING ANY TERMS OR CONDITIONS TO THE CONTRARY IN THE
# LICENSE AGREEMENT, IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY
# SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THESE LICENSED DELIVERABLES.
#
# U.S. Government End Users.  These Licensed Deliverables are a
# "commercial item" as that term is defined at 48 C.F.R. 2.101 (OCT
# 1995), consisting of "commercial computer software" and "commercial
# computer software documentation" as such terms are used in 48
# C.F.R. 12.212 (SEPT 1995) and is provided to the U.S. Government
# only as a commercial end item.  Consistent with 48 C.F.R.12.212 and
# 48 C.F.R. 227.7202-1 through 227.7202-4 (JUNE 1995), all
# U.S. Government End Users acquire the Licensed Deliverables with
# only those rights set forth herein.
#
# Any use of the Licensed Deliverables in individual and commercial
# software must include, in the user documentation and internal
# comments to the code, the above Disclaimer and U.S. Government End
# Users Notice.
#

# This sample uses an ONNX ResNet50 Model to create a TensorRT Inference Engine
import random
from PIL import Image
import numpy as np

import pycuda.driver as cuda
# This import causes pycuda to automatically manage CUDA context creation and cleanup.
import pycuda.autoinit

import tensorrt as trt
from onnx_tensorrt.tensorrt_engine import Engine
import onnx 
import onnx_tensorrt.backend as backend
import calibrator

import sys, os
sys.path.insert(1, os.path.join(sys.path[0], ".."))
import common

from slowfast.config.defaults import get_cfg
from slowfast.datasets import loader

import os

cfg = get_cfg()

cfg.merge_from_file("/workspace/tensorrt/samples/python/introductory_parser_samples/SlowFast/configs/SLOWFAST_8x8_R50-UCF101.yaml")
cfg.NUM_GPUS = 1
cfg.TRAIN.BATCH_SIZE = 1

class ModelData(object):
    MODEL_PATH = "slow_fast_ucf101_batch1.onnx"
    DTYPE = trt.float32

TRT_LOGGER = trt.Logger(trt.Logger.WARNING)

def main():
    onnx_model_file = ModelData.MODEL_PATH
    data_path = "/workspace/Data/UCF-101"

    stream1 = calibrator.ImageBatchStream()
    calib = calibrator.PythonEntropyCalibrator(stream1)

    
    model = onnx.load('slow_fast_ucf101_batch1.onnx')
    engine = backend.prepare(model,calib=calib, device='CUDA:0')
    
    test_loader = loader.construct_loader(cfg, 'val')

    for cur_iter, (inputs_b, labels, _, meta) in enumerate(test_loader):
        
        inputs_b[0] = inputs_b[0].numpy()
        inputs_b[1] = inputs_b[1].numpy()
        import time

        outputs = engine.run(inputs_b)
        
        if(cur_iter==20):
            break

if __name__ == '__main__':
    main()