def __init__(self,
bottleneck2d,
time_dim=1,
time_padding=0,
frame=0,
num_segments=4):
super(BasicBlock3d, self).__init__()
spatial_stride = bottleneck2d.conv2.stride[0]
self.frame = frame
self.num_segments = num_segments
self.conv1 = inflate.inflate_conv(bottleneck2d.conv1,
time_dim=time_dim,
time_padding=time_padding,
center=False)
self.bn1 = inflate.inflate_batch_norm(bottleneck2d.bn1)
self.conv2 = inflate.inflate_conv(bottleneck2d.conv2,
time_dim=time_dim,
time_padding=time_padding,
time_stride=1,
center=False)
self.bn2 = inflate.inflate_batch_norm(bottleneck2d.bn2)
self.relu = torch.nn.ReLU(inplace=True)
if bottleneck2d.downsample is not None:
self.downsample = inflate_downsample(bottleneck2d.downsample,
time_stride=spatial_stride)
else:
self.downsample = None
self.stride = bottleneck2d.stride
def inflate_downsample(downsample2d, time_stride=1):
downsample3d = torch.nn.Sequential(
inflate.inflate_conv(downsample2d[0],
time_dim=1,
time_stride=1,
center=False),
inflate.inflate_batch_norm(downsample2d[1]))
return downsample3d
def __init__(self,
resnet2d,
frame_nb=16,
class_nb=1000,
conv_class=False,
num_segments=4,
test_mode=False,
fast_implementation=0):
"""
Args:
conv_class: Whether to use convolutional layer as classifier to
adapt to various number of frames
"""
super(I3ResNet, self).__init__()
self.conv_class = conv_class
self.num_segments = num_segments
self.frame = frame_nb
self.conv1 = inflate.inflate_conv(resnet2d.conv1,
time_dim=1,
time_padding=0,
center=False)
self.bn1 = inflate.inflate_batch_norm(resnet2d.bn1)
self.relu = torch.nn.ReLU(inplace=True)
self.maxpool = inflate.inflate_pool(resnet2d.maxpool,
time_dim=1,
time_padding=0,
time_stride=1)
self.layer1 = inflate_reslayer(resnet2d.layer1)
self.layer2 = inflate_reslayer(resnet2d.layer2,
num_R4D=2,
in_channels=512,
fast_implementation=fast_implementation,
num_segments=num_segments)
self.layer3 = inflate_reslayer(resnet2d.layer3,
time_dim=3,
time_padding=1)
self.layer4 = inflate_reslayer(resnet2d.layer4,
time_dim=3,
time_padding=1)
if conv_class:
self.avgpool = inflate.inflate_pool(resnet2d.avgpool, time_dim=1)
self.classifier = torch.nn.Conv3d(in_channels=2048,
out_channels=class_nb,
kernel_size=(1, 1, 1),
bias=True)
else:
final_time_dim = int(math.ceil(frame_nb))
if test_mode:
self.avgpool = nn.AvgPool3d((frame_nb, 8, 8))
else:
self.avgpool = nn.AvgPool3d((frame_nb, 7, 7))
def __init__(self,
resnet2d,
frame_nb=16,
class_nb=1000,
conv_class=False,
num_segments=1,
gtsn=False):
"""
Args:
conv_class: Whether to use convolutional layer as classifier to
adapt to various number of frames
"""
super(I3ResNet_18_34, self).__init__()
self.num_segments = num_segments
self.conv_class = conv_class
self.gtsn = gtsn
self.conv1 = inflate.inflate_conv(resnet2d.conv1,
time_dim=1,
time_padding=0,
center=False)
self.bn1 = inflate.inflate_batch_norm(resnet2d.bn1)
self.relu = torch.nn.ReLU(inplace=True)
self.maxpool = inflate.inflate_pool(resnet2d.maxpool,
time_dim=1,
time_padding=0,
time_stride=1)
self.layer1 = inflate_reslayer_18_34(resnet2d.layer1)
self.layer2 = inflate_reslayer_18_34(resnet2d.layer2,
num_R4D=3,
in_channels=128)
self.layer3 = inflate_reslayer_18_34(resnet2d.layer3,
time_dim=3,
time_padding=1,
num_R4D=3,
in_channels=256)
self.layer4 = inflate_reslayer_18_34(resnet2d.layer4,
time_dim=3,
time_padding=1)
if conv_class:
self.avgpool = inflate.inflate_pool(resnet2d.avgpool, time_dim=1)
self.classifier = torch.nn.Conv3d(in_channels=2048,
out_channels=class_nb,
kernel_size=(1, 1, 1),
bias=True)
else:
final_time_dim = int(math.ceil(frame_nb))
self.avgpool = inflate.inflate_pool(resnet2d.avgpool, time_dim=4)