File size: 3,245 Bytes
663494c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
# Copyright (c) OpenMMLab. All rights reserved.
import argparse
import time
import torch
from mmcv import Config
from mmcv.parallel import MMDataParallel
from mmcv.runner import load_checkpoint, wrap_fp16_model
import sys
sys.path.append('.')
from projects.mmdet3d_plugin.datasets.builder import build_dataloader
from projects.mmdet3d_plugin.datasets import custom_build_dataset
# from mmdet3d.datasets import build_dataloader, build_dataset
from mmdet3d.models import build_detector
#from tools.misc.fuse_conv_bn import fuse_module
def parse_args():
parser = argparse.ArgumentParser(description='MMDet benchmark a model')
parser.add_argument('config', help='test config file path')
parser.add_argument('--checkpoint', default=None, help='checkpoint file')
parser.add_argument('--samples', default=2000, help='samples to benchmark')
parser.add_argument(
'--log-interval', default=10, help='interval of logging')
parser.add_argument(
'--fuse-conv-bn',
action='store_true',
help='Whether to fuse conv and bn, this will slightly increase'
'the inference speed')
args = parser.parse_args()
return args
def main():
args = parse_args()
cfg = Config.fromfile(args.config)
# set cudnn_benchmark
if cfg.get('cudnn_benchmark', False):
torch.backends.cudnn.benchmark = True
cfg.model.pretrained = None
cfg.data.test.test_mode = True
# build the dataloader
# TODO: support multiple images per gpu (only minor changes are needed)
print(cfg.data.test)
dataset = custom_build_dataset(cfg.data.test)
data_loader = build_dataloader(
dataset,
samples_per_gpu=1,
workers_per_gpu=cfg.data.workers_per_gpu,
dist=False,
shuffle=False)
# build the model and load checkpoint
cfg.model.train_cfg = None
model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
fp16_cfg = cfg.get('fp16', None)
if fp16_cfg is not None:
wrap_fp16_model(model)
if args.checkpoint is not None:
load_checkpoint(model, args.checkpoint, map_location='cpu')
#if args.fuse_conv_bn:
# model = fuse_module(model)
model = MMDataParallel(model, device_ids=[0])
model.eval()
# the first several iterations may be very slow so skip them
num_warmup = 5
pure_inf_time = 0
# benchmark with several samples and take the average
for i, data in enumerate(data_loader):
torch.cuda.synchronize()
start_time = time.perf_counter()
with torch.no_grad():
model(return_loss=False, rescale=True, **data)
torch.cuda.synchronize()
elapsed = time.perf_counter() - start_time
if i >= num_warmup:
pure_inf_time += elapsed
if (i + 1) % args.log_interval == 0:
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Done image [{i + 1:<3}/ {args.samples}], '
f'fps: {fps:.1f} img / s')
if (i + 1) == args.samples:
pure_inf_time += elapsed
fps = (i + 1 - num_warmup) / pure_inf_time
print(f'Overall fps: {fps:.1f} img / s')
break
if __name__ == '__main__':
main()
|