def test_get_all_models():
cfg = get_cfg_defaults()
names = get_model_list()
for name in names:
cfg.CONFIG.MODEL.NAME = name
net = get_model(cfg)
assert isinstance(net, nn.Module), '{}'.format(name)
def load_model(self, model_prefix, device_ctx):
if not self.torch:
with open('{}.json'.format(model_prefix), 'r') as f:
model_json = f.read()
model_lib = tvm.runtime.load_module('{}.so'.format(model_prefix))
with open('{}.params'.format(model_prefix), "rb") as f:
model_params = bytearray(f.read())
module = graph_runtime.create(model_json, model_lib, device_ctx)
module.load_params(model_params)
return module
import torch
from gluoncv.torch import model_zoo
from gluoncv.torch.engine.config import get_cfg_defaults
torch.set_grad_enabled(False)
device = torch.device('cuda')
cfg = get_cfg_defaults(name='directpose')
# cfg.merge_from_file('./configurations/ms_dla_34_4x_syncbn.yaml')
# net = model_zoo.dla34_fpn_directpose(cfg).to(device).eval()
# model = torch.load('model_final.pth')['model']
cfg.merge_from_file('./configurations/ms_aa_resnet50_4x_syncbn.yaml')
net = model_zoo.directpose_resnet_lpf_fpn(cfg).to(device).eval()
model = torch.load('model_final_resnet.pth')['model']
# _ = net(torch.zeros((1,3, self.image_height, self.image_width)).cuda())
net.load_state_dict(model, strict=False)
return net
def _test_model_list(model_list, use_cuda, x, pretrained, num_classes, **kwargs):
cfg = get_cfg_defaults()
for model in model_list:
cfg.CONFIG.MODEL.NAME = model
cfg.CONFIG.MODEL.PRETRAINED = pretrained
cfg.CONFIG.DATA.NUM_CLASSES = num_classes
net = get_model(cfg)
if use_cuda:
net.cuda()
x = x.cuda()
net(x)
# step lr scheduler
scheduler.step_rop(det_best_field_current, True)
logger.info(f"ROP: model improved: {is_best}, "
f"value {det_best_field_current:.3f},"
f"new LR: {optimizer.param_groups[0]['lr']:5.3e}")
if epoch % cfg.CONFIG.LOG.SAVE_FREQ == 0:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
model.save_model(optimizer, epoch, cfg)
# check if model did not improve for too long
term_after = 15
if epoch - best_epoch > term_after:
logger.info(f"NO improvements for {term_after} epochs (current "
f"{epoch} best {best_epoch}) STOP training.")
break
if writer is not None:
writer.close()
if logger is not None:
close_logger(logger)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Train Coot model.')
parser.add_argument('--config-file', type=str, help='path to config file.')
args = parser.parse_args()
cfg = get_cfg_defaults()
cfg.merge_from_file(args.config_file)
main_worker(cfg)
# step lr scheduler
scheduler.step_rop(det_best_field_current, True)
logger.info(f"ROP: model improved: {is_best}, "
f"value {det_best_field_current:.3f},"
f"new LR: {optimizer.param_groups[0]['lr']:5.3e}")
if epoch % cfg.CONFIG.LOG.SAVE_FREQ == 0:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
model.save_model(optimizer, epoch, cfg)
# check if model did not improve for too long
term_after = 15
if epoch - best_epoch > term_after:
logger.info(f"NO improvements for {term_after} epochs (current "
f"{epoch} best {best_epoch}) STOP training.")
break
if writer is not None:
writer.close()
if logger is not None:
close_logger(logger)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Train Coot model.')
parser.add_argument('--config-file', type=str, help='path to config file.')
args = parser.parse_args()
cfg = get_cfg_defaults(name='coot')
cfg.merge_from_file(args.config_file)
main_worker(cfg)
parser.add_argument("opts",
help="Modify config options using the command-line",
default=None,
nargs=argparse.REMAINDER)
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
torch.set_grad_enabled(False)
if args.use_gpu:
device = torch.device('cuda')
else:
device = torch.device('cpu')
cfg = get_cfg_defaults(name='directpose')
if args.model_name:
cfg.CONFIG.MODEL.PRETRAINED = True
cfg.CONFIG.MODEL.NAME = args.model_name
cfg.CONFIG.MODEL.TVM_MODE = True
net = model_zoo.get_model(cfg)
else:
assert os.path.isfile(args.config_file)
assert os.path.isfile(cfg.CONFIG.MODEL.PRETRAINED_PATH)
cfg.merge_from_file(args.config_file)
cfg.CONFIG.MODEL.TVM_MODE = True
net = model_zoo.directpose_resnet_lpf_fpn(cfg).to(device).eval()
load_model = torch.load(cfg.CONFIG.MODEL.PRETRAINED_PATH)
net.load_state_dict(load_model, strict=False)
images, orig_image = get_image(
'soccer.png',
cfg,
writer=writer)
if cfg.CONFIG.TRAIN.USE_WARMUP:
scheduler_warmup.step()
else:
scheduler.step()
# evaluation
if epoch % cfg.CONFIG.VAL.FREQ == 0 or epoch == cfg.CONFIG.TRAIN.EPOCH_NUM - 1:
validation_classification(model, val_loader, epoch, criterion, cfg,
writer)
# save model
if epoch % cfg.CONFIG.LOG.SAVE_FREQ == 0 or epoch == cfg.CONFIG.TRAIN.EPOCH_NUM - 1:
if cfg.DDP_CONFIG.GPU_WORLD_RANK == 0 or cfg.DDP_CONFIG.DISTRIBUTED == False:
save_model(model, optimizer, epoch, cfg)
if writer is not None:
writer.close()
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Train video action recognition models.')
parser.add_argument('--config-file', type=str, help='path to config file.')
args = parser.parse_args()
cfg = get_cfg_defaults(name='action_recognition')
cfg.merge_from_file(args.config_file)
spawn_workers(main_worker, cfg)
def test_model_zoo_tvm_export_directpose():
from gluoncv.torch.utils.tvm_utils.nms import nms
from tvm.contrib.download import download_testdata
def get_image(img_name='street_small.jpg',
img_url=None,
img_width=1280,
img_height=736):
def get_single_image_input(img_url):
img_name = img_url.split("/")[-1]
img_path = download_testdata(img_url, img_name, module="data")
orig_img = Image.open(img_path)
orig_img = orig_img.resize((img_width, img_height), Image.LANCZOS)
img = np.array(orig_img)[:, :, (0, 1, 2)].astype('uint8')
return img, orig_img, img_path
def get_transforms():
tforms = T.Compose([
T.ToTensor(),
T.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
return tforms
if img_url is None:
img_url = f"https://raw.githubusercontent.com/dmlc/web-data/master/gluoncv/detection/{img_name}"
img, orig_img, img_path = get_single_image_input(img_url)
tforms = get_transforms()
input_data = tforms(img).unsqueeze(0)
return input_data, orig_img
images, orig_img = get_image()
model_list = ['directpose_resnet50_lpf_fpn_coco']
cfg = get_cfg_defaults(name='directpose')
torch.set_grad_enabled(False)
use_cuda = True
if torch.cuda.device_count() == 0:
use_cuda = False
if use_cuda:
device = torch.device('cuda')
target = "cuda"
ctx = tvm.gpu(0)
else:
device = torch.device('cpu')
target = "llvm"
ctx = tvm.cpu()
for model in model_list:
cfg.CONFIG.MODEL.PRETRAINED = True
cfg.CONFIG.MODEL.NAME = model
cfg.CONFIG.MODEL.TVM_MODE = True
net = model_zoo.get_model(cfg).to(device).eval()
# y = net(images.to(device))
with torch.no_grad():
scripted_model = torch.jit.trace(net.forward,
images.to(device)).eval()
input_name = "input0"
shape_list = [(input_name, images.shape)]
mod, params = relay.frontend.from_pytorch(scripted_model, shape_list,
{"torchvision::nms": nms})
target_host = "llvm"
with tvm.transform.PassContext(opt_level=3):
lib = relay.build(mod,
target=target,
target_host=target_host,
params=params)
