Spaces:
Runtime error
Runtime error
File size: 2,973 Bytes
8fc2b4e |
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 |
import torch.nn as nn
import torch.nn.functional as F
import cliport.utils.utils as utils
from cliport.models.resnet import IdentityBlock, ConvBlock
from cliport.models.core.unet import Up
from cliport.models.rn50_bert_lingunet_lat import RN50BertLingUNetLat
class RN50BertLingUNet(RN50BertLingUNetLat):
""" ImageNet RN50 & Bert with U-Net skip connections but without lateral connections """
def __init__(self, input_shape, output_dim, cfg, device, preprocess):
super().__init__(input_shape, output_dim, cfg, device, preprocess)
def _build_decoder(self):
self.conv1 = nn.Sequential(
nn.Conv2d(self.input_dim, 1024, kernel_size=3, stride=1, padding=1, bias=False),
nn.ReLU(True)
)
self.up1 = Up(2048, 1024 // self.up_factor, self.bilinear)
self.up2 = Up(1024, 512 // self.up_factor, self.bilinear)
self.up3 = Up(512, 256 // self.up_factor, self.bilinear)
self.layer1 = nn.Sequential(
ConvBlock(128, [64, 64, 64], kernel_size=3, stride=1, batchnorm=self.batchnorm),
IdentityBlock(64, [64, 64, 64], kernel_size=3, stride=1, batchnorm=self.batchnorm),
nn.UpsamplingBilinear2d(scale_factor=2),
)
self.layer2 = nn.Sequential(
ConvBlock(64, [32, 32, 32], kernel_size=3, stride=1, batchnorm=self.batchnorm),
IdentityBlock(32, [32, 32, 32], kernel_size=3, stride=1, batchnorm=self.batchnorm),
nn.UpsamplingBilinear2d(scale_factor=2),
)
self.layer3 = nn.Sequential(
ConvBlock(32, [16, 16, 16], kernel_size=3, stride=1, batchnorm=self.batchnorm),
IdentityBlock(16, [16, 16, 16], kernel_size=3, stride=1, batchnorm=self.batchnorm),
nn.UpsamplingBilinear2d(scale_factor=2),
)
self.conv2 = nn.Sequential(
nn.Conv2d(16, self.output_dim, kernel_size=1)
)
def forward(self, x, l):
x = self.preprocess(x, dist='clip')
in_type = x.dtype
in_shape = x.shape
x = x[:,:3] # select RGB
x, im = self.encode_image(x)
x = x.to(in_type)
# encode language
l_enc, l_emb, l_mask = self.encode_text(l)
l_input = l_emb if 'word' in self.lang_fusion_type else l_enc
l_input = l_input.to(dtype=x.dtype)
# encode image
assert x.shape[1] == self.input_dim
x = self.conv1(x)
x = self.lang_fuser1(x, l_input, x2_mask=l_mask, x2_proj=self.lang_proj1)
x = self.up1(x, im[-2])
x = self.lang_fuser2(x, l_input, x2_mask=l_mask, x2_proj=self.lang_proj2)
x = self.up2(x, im[-3])
x = self.lang_fuser3(x, l_input, x2_mask=l_mask, x2_proj=self.lang_proj3)
x = self.up3(x, im[-4])
for layer in [self.layer1, self.layer2, self.layer3, self.conv2]:
x = layer(x)
x = F.interpolate(x, size=(in_shape[-2], in_shape[-1]), mode='bilinear')
return x |