logger = logging.getLogger('')
logger.setLevel(logging.INFO)
logger.addHandler(filehandler)
logger.addHandler(streamhandler)
logger.info(opt)
# number of GPUs to use
num_gpus = opt.num_gpus
ctx = [mx.gpu(i) for i in range(num_gpus)]
#ctx = [mx.gpu(1)]
# Get the model
net = myget(name=opt.model,
nclass=opt.num_classes,
num_segments=opt.num_segments,
input_channel=opt.input_channel,
batch_normal=opt.partial_bn,
use_lateral=opt.use_lateral,
use_kinetics_pretrain=opt.use_kinetics_pretrain)
net.cast(opt.dtype)
net.collect_params().reset_ctx(ctx)
net1 = myget(name=opt.TranConv_model)
net1.cast(opt.dtype)
net1.collect_params().reset_ctx(ctx)
#logger.info(net)
if opt.resume_params is not '':
net.load_parameters(opt.resume_params, ctx=ctx)
#if opt.use_pretrained:
self.clip_grad = 40
self.log_interval = 10
self.scale_ratios = [1.0, 0.875, 0.75, 0.66]
self.save_frequency = 5
self.mode = None#'hybrid'
self.lr_mode ='step'
self.accumulate = 1.0
opt = config()
makedirs(opt.save_dir)
# number of GPUs to use
#ctx = [mx.gpu(i) for i in range(opt.num_gpus)]
ctx = [mx.gpu(1)]
#ctx = [mx.cpu()]
# Get the model
net = myget(name=opt.model, nclass=opt.num_classes, num_segments=opt.num_segments,input_channel=opt.input_channel,partial_bn=opt.partial_bn)
net.cast(opt.dtype)
net.collect_params().reset_ctx(ctx)
#print(net)
if opt.mode == 'hybrid':
net.hybridize(static_alloc=True, static_shape=True)
transform_train = video.VideoGroupTrainTransform(size=(opt.input_size, opt.input_size), scale_ratios=opt.scale_ratios, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
transform_test = video.VideoGroupValTransform(size=opt.input_size, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
# Calculate effective total batch size
#
train_dataset = UCF101(setting=opt.train_setting, root=opt.train_dir, train=True,
new_width=opt.new_width, new_height=opt.new_height, new_length= (opt.new_length if opt.new_length==opt.new_length_diff else opt.new_length_diff),
target_width=opt.input_size, target_height=opt.input_size,
from gluoncv.data.transforms import video
from gluoncv.data import ucf101
from gluoncv.model_zoo import get_model
from gluoncv.utils import makedirs, LRSequential, LRScheduler, split_and_load, TrainingHistory
from model_zoo import get_model as myget
# number of GPUs to use
num_gpus = 1
#ctx = [mx.gpu(i) for i in range(num_gpus)]
ctx = [mx.gpu(1)]
# Get the model
#net = get_model(name='vgg16_ucf101', nclass=101, num_segments=3)
#net = myget(name='simple', nclass=101, num_segments=3)
net = myget('mseloss_vgg16', nclass=101, num_segments=3)
net.collect_params().reset_ctx(ctx)
#print(net)
transform_train = transforms.Compose([
# Fix the input video frames size as 256×340 and randomly sample the cropping width and height from
# {256,224,192,168}. After that, resize the cropped regions to 224 × 224.
video.VideoMultiScaleCrop(size=(224, 224),
scale_ratios=[1.0, 0.875, 0.75, 0.66]),
# Randomly flip the video frames horizontally
video.VideoRandomHorizontalFlip(),
# Transpose the video frames from height*width*num_channels to num_channels*height*width
# and map values from [0, 255] to [0,1]
video.VideoToTensor(),
# Normalize the video frames with mean and standard deviation calculated across all images
streamhandler = logging.StreamHandler()
logger = logging.getLogger('')
logger.setLevel(logging.INFO)
logger.addHandler(filehandler)
logger.addHandler(streamhandler)
logger.info(opt)
# number of GPUs to use
num_gpus = opt.num_gpus
ctx = [mx.gpu(i) for i in range(num_gpus)]
#ctx = [mx.gpu(1)]
# Get the model
net = myget(name=opt.model,
nclass=opt.num_classes,
num_segments=opt.num_segments,
input_channel=opt.input_channel,
batch_normal=opt.partial_bn,
pretrained_base=opt.pretrained_base)
net.cast(opt.dtype)
net.collect_params().reset_ctx(ctx)
#logger.info(net)
if opt.resume_params is not '':
net.load_parameters(opt.resume_params, ctx=ctx)
transform_train = video.VideoGroupTrainTransform(
size=(opt.input_size, opt.input_size),
scale_ratios=[1.0, 0.875, 0.75, 0.66],
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
transform_test = video.VideoGroupValTransform(size=opt.input_size,
mean=[0.485, 0.456, 0.406],
logger = logging.getLogger('')
logger.setLevel(logging.INFO)
logger.addHandler(filehandler)
logger.addHandler(streamhandler)
logger.info(opt)
# number of GPUs to use
num_gpus = opt.num_gpus
ctx = [mx.gpu(i) for i in range(num_gpus)]
#ctx = [mx.gpu(1)]
# Get the model
#net = get_dualnet(fgs_model=opt.fgsmodel,bgs_model=opt.bgsmodel,fgs_path=opt.fgs_params,bgs_path=opt.bgs_params, nclass=opt.num_classes, num_segments=opt.num_segments,input_channel=opt.input_channel,fusion_method=opt.fusion_method)
net_bgs = myget(name=opt.bgsmodel,
nclass=opt.num_classes,
num_segments=opt.num_segments,
input_channel=opt.input_channel,
batch_normal=opt.partial_bn)
net_fgs = myget(name=opt.fgsmodel,
nclass=opt.num_classes,
num_segments=opt.num_segments,
input_channel=opt.input_channel,
batch_normal=opt.partial_bn)
net_bgs.cast(opt.dtype)
net_bgs.collect_params().reset_ctx(ctx)
net_fgs.cast(opt.dtype)
net_fgs.collect_params().reset_ctx(ctx)
#logger.info(net)
if opt.bgs_params is not '':
net_bgs.load_parameters(opt.bgs_params, ctx=ctx)
if opt.fgs_params is not '':
