|
- # Copyright (c) OpenMMLab. All rights reserved.
- import argparse
- import copy
- import os
- import os.path as osp
- import time
- import warnings
- import shutil
- import sys
- path = os.path.dirname(os.path.dirname(__file__))
- print(path)
- sys.path.append("/tmp/code/code_test")
- os.system("pip install --no-cache-dir onnx==1.11.0 onnxruntime==1.11.1 protobuf==3.20.0")
- #os.environ['RANK'] = "0"
- #os.environ['WORLD_SIZE'] = "8"
- #os.environ['MASTER_ADDR'] = "localhost"
- #os.environ['MASTER_PORT'] = "1234"
- import mmcv
- import torch
- #os.environ["CUDA_VISIBLE_DEVICES"] = "0, 1, 2, 3"
- from mmcv import Config, DictAction
- from mmcv.runner import get_dist_info, init_dist
- from mmcv.utils import get_git_hash
- from pycocotools.coco import COCO
-
- from mmdet import __version__
- from mmdet.apis import init_random_seed, set_random_seed, train_detector
- from mmdet.datasets import build_dataset
- from mmdet.models import build_detector
- from mmdet.utils import collect_env, get_root_logger
-
- # Copyright (c) OpenMMLab. All rights reserved.
- from functools import partial
- import numpy as np
- from sklearn.covariance import LedoitWolf
- from mmdet.core.export import build_model_from_cfg, preprocess_example_input
- from mmdet.core.export.model_wrappers import ONNXRuntimeDetector
- from mmdet.apis import (async_inference_detector, inference_detector,
- init_detector, show_result_pyplot)
- import onnxruntime as ort
- import onnx
- print(f"onnxruntime device: {ort.get_device()}") # output: GPU
- print(f'ort avail providers: {ort.get_available_providers()}') # output: ['CUDAExecutionProvider', 'CPUExecutionProvider']
-
- def parse_normalize_cfg(test_pipeline):
- transforms = None
- for pipeline in test_pipeline:
- if 'transforms' in pipeline:
- transforms = pipeline['transforms']
- break
- assert transforms is not None, 'Failed to find `transforms`'
- norm_config_li = [_ for _ in transforms if _['type'] == 'Normalize']
- assert len(norm_config_li) == 1, '`norm_config` should only have one'
- norm_config = norm_config_li[0]
- return norm_config
-
- def pytorch2onnx(model,
- input_img,
- input_shape,
- normalize_cfg,
- opset_version=11,
- show=False,
- output_file='model.onnx',
- verify=False,
- test_img=None,
- do_simplify=False,
- dynamic_export=True,
- skip_postprocess=False):
-
- input_config = {
- 'input_shape': input_shape,
- 'input_path': input_img,
- 'normalize_cfg': normalize_cfg
- }
- # prepare input
- one_img, one_meta = preprocess_example_input(input_config)
- img_list, img_meta_list = [one_img], [[one_meta]]
-
- if skip_postprocess:
- warnings.warn('Not all models support export onnx without post '
- 'process, especially two stage detectors!')
- model.forward = model.forward_dummy
- torch.onnx.export(
- model,
- one_img,
- output_file,
- input_names=['input'],
- export_params=True,
- keep_initializers_as_inputs=True,
- do_constant_folding=True,
- verbose=show,
- opset_version=opset_version)
-
- print(f'Successfully exported ONNX model without '
- f'post process: {output_file}')
- return
-
- # replace original forward function
- origin_forward = model.forward
- model.forward = partial(
- model.forward,
- img_metas=img_meta_list,
- return_loss=False,
- rescale=False)
-
- output_names = ['dets', 'labels', 'feature', 'entropy', 'learning_loss']
- if model.with_mask:
- output_names.append('masks')
- input_name = 'input'
- dynamic_axes = None
- if dynamic_export:
- dynamic_axes = {
- input_name: {
- 0: 'batch',
- 2: 'height',
- 3: 'width'
- },
- 'dets': {
- 0: 'batch',
- 1: 'num_dets',
- },
- 'labels': {
- 0: 'batch',
- 1: 'num_dets',
- },
- 'feature': {
- 0: 'batch',
- 1: 'feat_dim',
- },
- 'entropy': {
- 0: 'batch',
- 1: '1',
- },
- 'learning_loss': {
- 0: 'batch',
- 1: '1',
- },
- }
- if model.with_mask:
- dynamic_axes['masks'] = {0: 'batch', 1: 'num_dets'}
-
- torch.onnx.export(
- model,
- img_list,
- output_file,
- input_names=[input_name],
- output_names=output_names,
- export_params=True,
- keep_initializers_as_inputs=True,
- do_constant_folding=True,
- verbose=show,
- opset_version=opset_version,
- dynamic_axes=dynamic_axes)
-
- model.forward = origin_forward
-
- # get the custom op path
- ort_custom_op_path = ''
- try:
- from mmcv.ops import get_onnxruntime_op_path
- ort_custom_op_path = get_onnxruntime_op_path()
- except (ImportError, ModuleNotFoundError):
- warnings.warn('If input model has custom op from mmcv, \
- you may have to build mmcv with ONNXRuntime from source.')
-
- if do_simplify:
- import onnxsim
-
- from mmdet import digit_version
-
- min_required_version = '0.3.0'
- assert digit_version(onnxsim.__version__) >= digit_version(
- min_required_version
- ), f'Requires to install onnx-simplify>={min_required_version}'
-
- input_dic = {'input': img_list[0].detach().cpu().numpy()}
- model_opt, check_ok = onnxsim.simplify(
- output_file,
- input_data=input_dic,
- custom_lib=ort_custom_op_path,
- dynamic_input_shape=dynamic_export)
- if check_ok:
- onnx.save(model_opt, output_file)
- print(f'Successfully simplified ONNX model: {output_file}')
- else:
- warnings.warn('Failed to simplify ONNX model.')
- print(f'Successfully exported ONNX model: {output_file}')
-
- if verify:
- # check by onnx
- onnx_model = onnx.load(output_file)
- onnx.checker.check_model(onnx_model)
-
- # wrap onnx model
- onnx_model = ONNXRuntimeDetector(output_file, model.CLASSES, 0)
- if dynamic_export:
- # scale up to test dynamic shape
- h, w = [int((_ * 1.5) // 32 * 32) for _ in input_shape[2:]]
- h, w = min(1344, h), min(1344, w)
- input_config['input_shape'] = (1, 3, h, w)
-
- if test_img is None:
- input_config['input_path'] = input_img
-
- # prepare input once again
- one_img, one_meta = preprocess_example_input(input_config)
- img_list, img_meta_list = [one_img], [[one_meta]]
-
- # get pytorch output
- with torch.no_grad():
- pytorch_results = model(
- img_list,
- img_metas=img_meta_list,
- return_loss=False,
- rescale=True)[0]
-
- img_list = [_.cuda().contiguous() for _ in img_list]
- if dynamic_export:
- img_list = img_list + [_.flip(-1).contiguous() for _ in img_list]
- img_meta_list = img_meta_list * 2
- # get onnx output
- onnx_results = onnx_model(
- img_list, img_metas=img_meta_list, return_loss=False)[0]
- # visualize predictions
- score_thr = 0.3
- if show:
- out_file_ort, out_file_pt = None, None
- else:
- out_file_ort, out_file_pt = 'show-ort.png', 'show-pt.png'
-
- show_img = one_meta['show_img']
- model.show_result(
- show_img,
- pytorch_results,
- score_thr=score_thr,
- show=True,
- win_name='PyTorch',
- out_file=out_file_pt)
- onnx_model.show_result(
- show_img,
- onnx_results,
- score_thr=score_thr,
- show=True,
- win_name='ONNXRuntime',
- out_file=out_file_ort)
-
- # compare a part of result
- '''print(input_config['input_shape'])
- print(one_img)
- print(len(onnx_results))
- print(len(pytorch_results))
- print(onnx_results)
- print(pytorch_results)'''
- for i in range(len(onnx_results)):
- print(onnx_results[i].shape)
- print("***************")
- for i in range(len(pytorch_results)):
- print(pytorch_results[i].shape)
- if model.with_mask:
- compare_pairs = list(zip(onnx_results, pytorch_results))
- else:
- compare_pairs = [(onnx_results, pytorch_results)]
- err_msg = 'The numerical values are different between Pytorch' + \
- ' and ONNX, but it does not necessarily mean the' + \
- ' exported ONNX model is problematic.'
- # check the numerical value
- for onnx_res, pytorch_res in compare_pairs:
- for o_res, p_res in zip(onnx_res, pytorch_res):
- np.testing.assert_allclose(
- o_res, p_res, rtol=1e-03, atol=1e-05, err_msg=err_msg)
- print('The numerical values are the same between Pytorch and ONNX')
- def parse_args():
- parser = argparse.ArgumentParser(description='Train a detector')
- parser.add_argument('--config', default='/tmp/code/code_test/configs/AD_mlops/AD_mlops_test18.py', help='train config file path')
- parser.add_argument('--work-dir',default='/tmp/output', help='the dir to save logs and models')
- parser.add_argument(
- '--resume-from', help='the checkpoint file to resume from')
- parser.add_argument(
- '--no-validate',
- action='store_true',
- help='whether not to evaluate the checkpoint during training')
- parser.add_argument(
- '--shape',
- help='infer image shape')
- group_gpus = parser.add_mutually_exclusive_group()
- group_gpus.add_argument(
- '--gpus',
- type=int,
- help='number of gpus to use '
- '(only applicable to non-distributed training)')
- group_gpus.add_argument(
- '--gpu-ids',
- type=int,
- nargs='+',
- help='ids of gpus to use '
- '(only applicable to non-distributed training)')
- parser.add_argument('--seed', type=int, default=None, help='random seed')
- parser.add_argument(
- '--deterministic',
- action='store_true',
- help='whether to set deterministic options for CUDNN backend.')
- parser.add_argument(
- '--options',
- nargs='+',
- action=DictAction,
- help='override some settings in the used config, the key-value pair '
- 'in xxx=yyy format will be merged into config file (deprecate), '
- 'change to --cfg-options instead.')
- parser.add_argument(
- '--cfg-options',
- nargs='+',
- action=DictAction,
- help='override some settings in the used config, the key-value pair '
- 'in xxx=yyy format will be merged into config file. If the value to '
- 'be overwritten is a list, it should be like key="[a,b]" or key=a,b '
- 'It also allows nested list/tuple values, e.g. key="[(a,b),(c,d)]" '
- 'Note that the quotation marks are necessary and that no white space '
- 'is allowed.')
- parser.add_argument(
- '--launcher',
- choices=['none', 'pytorch', 'slurm', 'mpi'],
- default='none',
- help='job launcher')
- parser.add_argument('--local_rank', type=int, default=0)
- parser.add_argument(
- '--data-path', default='/tmp/dataset', help='dataset path')
- parser.add_argument(
- '--batchsize',
- type=int,
- default=8,
- help='training batch size')
- parser.add_argument(
- '--epoch',
- type=int,
- default=2,
- help='training epoch')
- parser.add_argument(
- '--warmup_iters',
- type=int,
- default=500,
- help='training warmup_iters')
- parser.add_argument(
- '--lr',
- type=float,
- default=0.001,
- help='learning rate')
- parser.add_argument('--train_image_size',
- type=list,
- default=[(100, 100)],
- help='train image size')
- parser.add_argument('--test_image_size',
- type=list,
- default=[(100, 100)],
- help='test image size')
- args = parser.parse_args()
- if 'LOCAL_RANK' not in os.environ:
- os.environ['LOCAL_RANK'] = str(args.local_rank)
-
- if args.options and args.cfg_options:
- raise ValueError(
- '--options and --cfg-options cannot be both '
- 'specified, --options is deprecated in favor of --cfg-options')
- if args.options:
- warnings.warn('--options is deprecated in favor of --cfg-options')
- args.cfg_options = args.options
-
- return args
-
-
- def main():
- args = parse_args()
-
- cfg = Config.fromfile(args.config)
- if args.cfg_options is not None:
- cfg.merge_from_dict(args.cfg_options)
- # import modules from string list.
- if cfg.get('custom_imports', None):
- from mmcv.utils import import_modules_from_strings
- import_modules_from_strings(**cfg['custom_imports'])
- # set cudnn_benchmark
- if cfg.get('cudnn_benchmark', False):
- torch.backends.cudnn.benchmark = True
-
- if args.batchsize is not None:
- cfg.data.samples_per_gpu = args.batchsize
- if args.epoch is not None:
- cfg.runner.max_epochs = args.epoch
- if args.warmup_iters is not None:
- cfg.lr_config.warmup_iters = args.warmup_iters
- if args.lr is not None:
- cfg.optimizer.lr = args.lr
- '''if args.train_image_size is not None:
- cfg.train_pipeline[2].img_scale = args.train_image_size
- cfg.data.train.dataset.pipeline[2].img_scale = args.train_image_size'''
- if args.test_image_size is not None:
- cfg.test_pipeline[1].img_scale = args.test_image_size
- cfg.data.val.pipeline[1].img_scale = args.test_image_size
- cfg.data.test.pipeline[1].img_scale = args.test_image_size
- #if on platform, change the classnum fit the user define dataset
- if args.data_path is not None:
- coco_config=COCO(os.path.join(args.data_path,"annotations/instances_annotations.json"))
- cfg.data.train.img_prefix = os.path.join(args.data_path,"images")
- cfg.data.train.ann_file = os.path.join(args.data_path,"annotations/instances_annotations.json")
-
- cfg.data.val.img_prefix = os.path.join(args.data_path,"images")
- cfg.data.val.ann_file = os.path.join(args.data_path,"annotations/instances_annotations.json")
-
- cfg.data.test.img_prefix = os.path.join(args.data_path,"images")
- cfg.data.test.ann_file = os.path.join(args.data_path,"annotations/instances_annotations.json")
- cfg.classes = ()
- for cat in coco_config.cats.values():
- cfg.classes = cfg.classes + tuple([cat['name']])
-
- cfg.data.train.classes = cfg.classes
- cfg.data.val.classes = cfg.classes
- cfg.data.test.classes = cfg.classes
-
- #some model will RepeatDataset to speed up training, make sure all dataset path replace to data_path
- #cfg = Config.fromstring(cfg.dump().replace("ann_file='data/coco/annotations/instances_train2017.json',","ann_file='{}',".format(os.path.join(args.data_path,"annotations/instances_annotations.json"))), ".py")
- #cfg = Config.fromstring(cfg.dump().replace("img_prefix='data/coco/train2017/',","img_prefix='{}',".format(os.path.join(args.data_path,"images"))), ".py")
-
- # replace the classes num fit userdefine dataset
- #cfg = Config.fromstring(cfg.dump().replace("num_classes=80","num_classes={0}".format(len(coco_config.getCatIds()))), ".py")
- cfg.model.bbox_head.num_classes = len(coco_config.getCatIds())
- print(cfg.dump())
- # work_dir is determined in this priority: CLI > segment in file > filename
- if args.work_dir is not None:
- # update configs according to CLI args if args.work_dir is not None
- cfg.work_dir = args.work_dir
- elif cfg.get('work_dir', None) is None:
- # use config filename as default work_dir if cfg.work_dir is None
- cfg.work_dir = osp.join('./work_dirs',
- osp.splitext(osp.basename(args.config))[0])
- if args.resume_from is not None:
- cfg.resume_from = args.resume_from
- if args.gpu_ids is not None:
- cfg.gpu_ids = args.gpu_ids
- else:
- cfg.gpu_ids = range(1) if args.gpus is None else range(args.gpus)
-
- # init distributed env first, since logger depends on the dist info.
- if args.launcher == 'none':
- distributed = False
- else:
- distributed = True
- init_dist(args.launcher, **cfg.dist_params)
- # re-set gpu_ids with distributed training mode
- _, world_size = get_dist_info()
- cfg.gpu_ids = range(world_size)
-
- # create work_dir
- mmcv.mkdir_or_exist(osp.abspath(cfg.work_dir))
- # dump config
- cfg.dump(osp.join(cfg.work_dir, 'config.py'))
- # init the logger before other steps
- timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
- log_file = osp.join(cfg.work_dir, f'{timestamp}.log')
- logger = get_root_logger(log_file=log_file, log_level=cfg.log_level)
-
- # init the meta dict to record some important information such as
- # environment info and seed, which will be logged
- meta = dict()
- # log env info
- env_info_dict = collect_env()
- env_info = '\n'.join([(f'{k}: {v}') for k, v in env_info_dict.items()])
- dash_line = '-' * 60 + '\n'
- logger.info('Environment info:\n' + dash_line + env_info + '\n' +
- dash_line)
- meta['env_info'] = env_info
- meta['config'] = cfg.pretty_text
- # log some basic info
- logger.info(f'Distributed training: {distributed}')
- logger.info(f'Config:\n{cfg.pretty_text}')
-
- # set random seeds
- #seed = init_random_seed(args.seed)
- seed = 965702173
- logger.info(f'Set random seed to {seed}, '
- f'deterministic: {args.deterministic}')
- set_random_seed(seed, deterministic=args.deterministic)
- #set_random_seed(seed, deterministic=True)
- cfg.seed = seed
- meta['seed'] = seed
- meta['exp_name'] = osp.basename(args.config)
-
- model = build_detector(
- cfg.model,
- train_cfg=cfg.get('train_cfg'),
- test_cfg=cfg.get('test_cfg'))
- model.init_weights()
-
- datasets = [build_dataset(cfg.data.train)]
- if len(cfg.workflow) == 2:
- val_dataset = copy.deepcopy(cfg.data.val)
- val_dataset.pipeline = cfg.data.train.pipeline
- datasets.append(build_dataset(val_dataset))
- if cfg.checkpoint_config is not None:
- # save mmdet version, config file content and class names in
- # checkpoints as meta data
- cfg.checkpoint_config.meta = dict(
- mmdet_version=__version__ + get_git_hash()[:7],
- CLASSES=datasets[0].CLASSES)
- # add an attribute for visualization convenience
- model.CLASSES = datasets[0].CLASSES
- train_detector(
- model,
- datasets,
- cfg,
- distributed=distributed,
- validate=(not args.no_validate),
- timestamp=timestamp,
- meta=meta)
-
- if args.shape is None:
- img_scale = cfg.test_pipeline[1]['img_scale'][0]
- print(img_scale)
- input_shape = (1, 3, img_scale[1], img_scale[0])
- elif len(args.shape) == 1:
- input_shape = (1, 3, args.shape[0], args.shape[0])
- elif len(args.shape) == 2:
- input_shape = (1, 3) + tuple(args.shape)
- else:
- raise ValueError('invalid input shape')
- # create onnx dir
- onnx_path = osp.join(args.work_dir)
- model = build_model_from_cfg(osp.join(args.work_dir, 'config.py'), osp.join(args.work_dir, "latest.pth"))
- input_img = osp.join(osp.dirname(__file__), 'demo.jpg')
- normalize_cfg = parse_normalize_cfg(cfg.test_pipeline)
-
- # convert model to onnx file
- pytorch2onnx(
- model,
- input_img,
- input_shape,
- normalize_cfg,
- output_file=osp.join(onnx_path,'model.onnx'),
- test_img=input_img)
-
- #启智平台
- shutil.copytree(osp.abspath(osp.join(osp.dirname(__file__),'../transformer/')), osp.join(args.work_dir, "transformer"))
- #shutil.copy(osp.join(args.train_work_dir, "config.py"), osp.join(args.work_dir, "config.py"))
- class_name_file = open(osp.join(args.work_dir, "class_names.txt"), 'w')
- for name in cfg.classes:
- class_name_file.write(name+'\n')
- shutil.copy(osp.abspath(osp.join(osp.dirname(__file__),'serve_desc.yaml')), osp.join(args.work_dir, "serve_desc.yaml"))
-
-
-
- if __name__ == '__main__':
- main()
|