mirror of
https://github.com/modelscope/modelscope.git
synced 2026-02-24 04:01:10 +01:00
update license and revert support camouflaged-detection from latest master
Link: https://code.alibaba-inc.com/Ali-MaaS/MaaS-lib/codereview/11892922 * update license and revert support camouflaged-detection from latest master
This commit is contained in:
wendi.hwd
3
data/test/images/image_camouflag_detection.jpg
Normal file
3
data/test/images/image_camouflag_detection.jpg
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c713215f7fb4da5382c9137347ee52956a7a44d5979c4cffd3c9b6d1d7e878f
|
||||
size 19445
|
||||
@@ -1,3 +1,4 @@
|
||||
# The implementation is adopted from U-2-Net, made publicly available under the Apache 2.0 License
|
||||
# source code avaiable via https://github.com/xuebinqin/U-2-Net
|
||||
from .senet import SENet
|
||||
from .u2net import U2NET
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
# Implementation in this file is modified based on Res2Net-PretrainedModels
|
||||
# Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
|
||||
# publicly available at https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net_v1b.py
|
||||
# Implementation in this file is modified based on SINet-V2,made publicly available under the Apache 2.0 License
|
||||
# publicly available at https://github.com/GewelsJI/SINet-V2
|
||||
import math
|
||||
|
||||
import torch
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
# Implementation in this file is modified based on Res2Net-PretrainedModels
|
||||
# Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International Public License
|
||||
# publicly available at https://github.com/Res2Net/Res2Net-PretrainedModels/blob/master/res2net_v1b.py
|
||||
# Implementation in this file is modified based on SINet-V2,made publicly available under the Apache 2.0 License
|
||||
# publicly available at https://github.com/GewelsJI/SINet-V2
|
||||
from .Res2Net_v1b import res2net50_v1b_26w_4s
|
||||
|
||||
__all__ = ['res2net50_v1b_26w_4s']
|
||||
|
||||
178
modelscope/models/cv/salient_detection/models/modules.py
Normal file
178
modelscope/models/cv/salient_detection/models/modules.py
Normal file
@@ -0,0 +1,178 @@
|
||||
# Copyright (c) Alibaba, Inc. and its affiliates.
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
from .utils import ConvBNReLU
|
||||
|
||||
|
||||
class AreaLayer(nn.Module):
|
||||
|
||||
def __init__(self, in_channel, out_channel):
|
||||
super(AreaLayer, self).__init__()
|
||||
self.lbody = nn.Sequential(
|
||||
nn.Conv2d(out_channel, out_channel, 1),
|
||||
nn.BatchNorm2d(out_channel), nn.ReLU(inplace=True))
|
||||
self.hbody = nn.Sequential(
|
||||
nn.Conv2d(in_channel, out_channel, 1), nn.BatchNorm2d(out_channel),
|
||||
nn.ReLU(inplace=True))
|
||||
self.body = nn.Sequential(
|
||||
nn.Conv2d(2 * out_channel, out_channel, 3, 1, 1),
|
||||
nn.BatchNorm2d(out_channel), nn.ReLU(inplace=True),
|
||||
nn.Conv2d(out_channel, out_channel, 3, 1, 1),
|
||||
nn.BatchNorm2d(out_channel), nn.ReLU(inplace=True),
|
||||
nn.Conv2d(out_channel, 1, 1))
|
||||
|
||||
def forward(self, xl, xh):
|
||||
xl1 = self.lbody(xl)
|
||||
xl1 = F.interpolate(
|
||||
xl1, size=xh.size()[2:], mode='bilinear', align_corners=True)
|
||||
xh1 = self.hbody(xh)
|
||||
x = torch.cat((xl1, xh1), dim=1)
|
||||
x_out = self.body(x)
|
||||
return x_out
|
||||
|
||||
|
||||
class EdgeLayer(nn.Module):
|
||||
|
||||
def __init__(self, in_channel, out_channel):
|
||||
super(EdgeLayer, self).__init__()
|
||||
self.lbody = nn.Sequential(
|
||||
nn.Conv2d(out_channel, out_channel, 1),
|
||||
nn.BatchNorm2d(out_channel), nn.ReLU(inplace=True))
|
||||
self.hbody = nn.Sequential(
|
||||
nn.Conv2d(in_channel, out_channel, 1), nn.BatchNorm2d(out_channel),
|
||||
nn.ReLU(inplace=True))
|
||||
self.bodye = nn.Sequential(
|
||||
nn.Conv2d(2 * out_channel, out_channel, 3, 1, 1),
|
||||
nn.BatchNorm2d(out_channel), nn.ReLU(inplace=True),
|
||||
nn.Conv2d(out_channel, out_channel, 3, 1, 1),
|
||||
nn.BatchNorm2d(out_channel), nn.ReLU(inplace=True),
|
||||
nn.Conv2d(out_channel, 1, 1))
|
||||
|
||||
def forward(self, xl, xh):
|
||||
xl1 = self.lbody(xl)
|
||||
xh1 = self.hbody(xh)
|
||||
xh1 = F.interpolate(
|
||||
xh1, size=xl.size()[2:], mode='bilinear', align_corners=True)
|
||||
x = torch.cat((xl1, xh1), dim=1)
|
||||
x_out = self.bodye(x)
|
||||
return x_out
|
||||
|
||||
|
||||
class EBlock(nn.Module):
|
||||
|
||||
def __init__(self, inchs, outchs):
|
||||
super(EBlock, self).__init__()
|
||||
self.elayer = nn.Sequential(
|
||||
ConvBNReLU(inchs + 1, outchs, kernel_size=3, padding=1, stride=1),
|
||||
ConvBNReLU(outchs, outchs, 1))
|
||||
self.salayer = nn.Sequential(
|
||||
nn.Conv2d(2, 1, 3, 1, 1, bias=False),
|
||||
nn.BatchNorm2d(1, momentum=0.01), nn.Sigmoid())
|
||||
|
||||
def forward(self, x, edgeAtten):
|
||||
x = torch.cat((x, edgeAtten), dim=1)
|
||||
ex = self.elayer(x)
|
||||
ex_max = torch.max(ex, 1, keepdim=True)[0]
|
||||
ex_mean = torch.mean(ex, dim=1, keepdim=True)
|
||||
xei_compress = torch.cat((ex_max, ex_mean), dim=1)
|
||||
|
||||
scale = self.salayer(xei_compress)
|
||||
x_out = ex * scale
|
||||
return x_out
|
||||
|
||||
|
||||
class StructureE(nn.Module):
|
||||
|
||||
def __init__(self, inchs, outchs, EM):
|
||||
super(StructureE, self).__init__()
|
||||
self.ne_modules = int(inchs / EM)
|
||||
NM = int(outchs / self.ne_modules)
|
||||
elayes = []
|
||||
for i in range(self.ne_modules):
|
||||
emblock = EBlock(EM, NM)
|
||||
elayes.append(emblock)
|
||||
self.emlayes = nn.ModuleList(elayes)
|
||||
self.body = nn.Sequential(
|
||||
ConvBNReLU(outchs, outchs, 3, 1, 1), ConvBNReLU(outchs, outchs, 1))
|
||||
|
||||
def forward(self, x, edgeAtten):
|
||||
if edgeAtten.size() != x.size():
|
||||
edgeAtten = F.interpolate(
|
||||
edgeAtten, x.size()[2:], mode='bilinear', align_corners=False)
|
||||
xx = torch.chunk(x, self.ne_modules, dim=1)
|
||||
efeas = []
|
||||
for i in range(self.ne_modules):
|
||||
xei = self.emlayes[i](xx[i], edgeAtten)
|
||||
efeas.append(xei)
|
||||
efeas = torch.cat(efeas, dim=1)
|
||||
x_out = self.body(efeas)
|
||||
return x_out
|
||||
|
||||
|
||||
class ABlock(nn.Module):
|
||||
|
||||
def __init__(self, inchs, outchs, k):
|
||||
super(ABlock, self).__init__()
|
||||
self.alayer = nn.Sequential(
|
||||
ConvBNReLU(inchs, outchs, k, 1, k // 2),
|
||||
ConvBNReLU(outchs, outchs, 1))
|
||||
self.arlayer = nn.Sequential(
|
||||
ConvBNReLU(inchs, outchs, k, 1, k // 2),
|
||||
ConvBNReLU(outchs, outchs, 1))
|
||||
self.fusion = ConvBNReLU(2 * outchs, outchs, 1)
|
||||
|
||||
def forward(self, x, areaAtten):
|
||||
xa = x * areaAtten
|
||||
xra = x * (1 - areaAtten)
|
||||
xout = self.fusion(torch.cat((xa, xra), dim=1))
|
||||
return xout
|
||||
|
||||
|
||||
class AMFusion(nn.Module):
|
||||
|
||||
def __init__(self, inchs, outchs, AM):
|
||||
super(AMFusion, self).__init__()
|
||||
self.k = [3, 3, 5, 5]
|
||||
self.conv_up = ConvBNReLU(inchs, outchs, 3, 1, 1)
|
||||
self.up = nn.Upsample(
|
||||
scale_factor=2, mode='bilinear', align_corners=True)
|
||||
self.na_modules = int(outchs / AM)
|
||||
alayers = []
|
||||
for i in range(self.na_modules):
|
||||
layer = ABlock(AM, AM, self.k[i])
|
||||
alayers.append(layer)
|
||||
self.alayers = nn.ModuleList(alayers)
|
||||
self.fusion_0 = ConvBNReLU(outchs, outchs, 3, 1, 1)
|
||||
self.fusion_e = nn.Sequential(
|
||||
nn.Conv2d(
|
||||
outchs, outchs, kernel_size=(3, 1), padding=(1, 0),
|
||||
bias=False), nn.BatchNorm2d(outchs), nn.ReLU(inplace=True),
|
||||
nn.Conv2d(
|
||||
outchs, outchs, kernel_size=(1, 3), padding=(0, 1),
|
||||
bias=False), nn.BatchNorm2d(outchs), nn.ReLU(inplace=True))
|
||||
self.fusion_e1 = nn.Sequential(
|
||||
nn.Conv2d(
|
||||
outchs, outchs, kernel_size=(5, 1), padding=(2, 0),
|
||||
bias=False), nn.BatchNorm2d(outchs), nn.ReLU(inplace=True),
|
||||
nn.Conv2d(
|
||||
outchs, outchs, kernel_size=(1, 5), padding=(0, 2),
|
||||
bias=False), nn.BatchNorm2d(outchs), nn.ReLU(inplace=True))
|
||||
self.fusion = ConvBNReLU(3 * outchs, outchs, 1)
|
||||
|
||||
def forward(self, xl, xh, xhm):
|
||||
xh1 = self.up(self.conv_up(xh))
|
||||
x = xh1 + xl
|
||||
xm = self.up(torch.sigmoid(xhm))
|
||||
xx = torch.chunk(x, self.na_modules, dim=1)
|
||||
xxmids = []
|
||||
for i in range(self.na_modules):
|
||||
xi = self.alayers[i](xx[i], xm)
|
||||
xxmids.append(xi)
|
||||
xfea = torch.cat(xxmids, dim=1)
|
||||
x0 = self.fusion_0(xfea)
|
||||
x1 = self.fusion_e(xfea)
|
||||
x2 = self.fusion_e1(xfea)
|
||||
x_out = self.fusion(torch.cat((x0, x1, x2), dim=1))
|
||||
return x_out
|
||||
74
modelscope/models/cv/salient_detection/models/senet.py
Normal file
74
modelscope/models/cv/salient_detection/models/senet.py
Normal file
@@ -0,0 +1,74 @@
|
||||
# Copyright (c) Alibaba, Inc. and its affiliates.
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
from .backbone import res2net50_v1b_26w_4s as res2net
|
||||
from .modules import AMFusion, AreaLayer, EdgeLayer, StructureE
|
||||
from .utils import ASPP, CBAM, ConvBNReLU
|
||||
|
||||
|
||||
class SENet(nn.Module):
|
||||
|
||||
def __init__(self, backbone_path=None, pretrained=False):
|
||||
super(SENet, self).__init__()
|
||||
resnet50 = res2net(backbone_path, pretrained)
|
||||
self.layer0_1 = nn.Sequential(resnet50.conv1, resnet50.bn1,
|
||||
resnet50.relu)
|
||||
self.maxpool = resnet50.maxpool
|
||||
self.layer1 = resnet50.layer1
|
||||
self.layer2 = resnet50.layer2
|
||||
self.layer3 = resnet50.layer3
|
||||
self.layer4 = resnet50.layer4
|
||||
self.aspp3 = ASPP(1024, 256)
|
||||
self.aspp4 = ASPP(2048, 256)
|
||||
self.cbblock3 = CBAM(inchs=256, kernel_size=5)
|
||||
self.cbblock4 = CBAM(inchs=256, kernel_size=5)
|
||||
self.up = nn.Upsample(
|
||||
mode='bilinear', scale_factor=2, align_corners=False)
|
||||
self.conv_up = ConvBNReLU(512, 512, 1)
|
||||
self.aux_edge = EdgeLayer(512, 256)
|
||||
self.aux_area = AreaLayer(512, 256)
|
||||
self.layer1_enhance = StructureE(256, 128, 128)
|
||||
self.layer2_enhance = StructureE(512, 256, 128)
|
||||
self.layer3_decoder = AMFusion(512, 256, 128)
|
||||
self.layer2_decoder = AMFusion(256, 128, 128)
|
||||
self.out_conv_8 = nn.Conv2d(256, 1, 1)
|
||||
self.out_conv_4 = nn.Conv2d(128, 1, 1)
|
||||
|
||||
def forward(self, x):
|
||||
layer0 = self.layer0_1(x)
|
||||
layer0s = self.maxpool(layer0)
|
||||
layer1 = self.layer1(layer0s)
|
||||
layer2 = self.layer2(layer1)
|
||||
layer3 = self.layer3(layer2)
|
||||
layer4 = self.layer4(layer3)
|
||||
layer3_eh = self.cbblock3(self.aspp3(layer3))
|
||||
layer4_eh = self.cbblock4(self.aspp4(layer4))
|
||||
layer34 = self.conv_up(
|
||||
torch.cat((self.up(layer4_eh), layer3_eh), dim=1))
|
||||
edge_atten = self.aux_edge(layer1, layer34)
|
||||
area_atten = self.aux_area(layer1, layer34)
|
||||
edge_atten_ = torch.sigmoid(edge_atten)
|
||||
layer1_eh = self.layer1_enhance(layer1, edge_atten_)
|
||||
layer2_eh = self.layer2_enhance(layer2, edge_atten_)
|
||||
layer2_fu = self.layer3_decoder(layer2_eh, layer34, area_atten)
|
||||
out_8 = self.out_conv_8(layer2_fu)
|
||||
layer1_fu = self.layer2_decoder(layer1_eh, layer2_fu, out_8)
|
||||
out_4 = self.out_conv_4(layer1_fu)
|
||||
out_16 = F.interpolate(
|
||||
area_atten,
|
||||
size=x.size()[2:],
|
||||
mode='bilinear',
|
||||
align_corners=False)
|
||||
out_8 = F.interpolate(
|
||||
out_8, size=x.size()[2:], mode='bilinear', align_corners=False)
|
||||
out_4 = F.interpolate(
|
||||
out_4, size=x.size()[2:], mode='bilinear', align_corners=False)
|
||||
edge_out = F.interpolate(
|
||||
edge_atten_,
|
||||
size=x.size()[2:],
|
||||
mode='bilinear',
|
||||
align_corners=False)
|
||||
|
||||
return out_4.sigmoid(), out_8.sigmoid(), out_16.sigmoid(), edge_out
|
||||
@@ -2,7 +2,6 @@
|
||||
import os.path as osp
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image
|
||||
from torchvision import transforms
|
||||
@@ -10,8 +9,9 @@ from torchvision import transforms
|
||||
from modelscope.metainfo import Models
|
||||
from modelscope.models.base.base_torch_model import TorchModel
|
||||
from modelscope.models.builder import MODELS
|
||||
from modelscope.utils.config import Config
|
||||
from modelscope.utils.constant import ModelFile, Tasks
|
||||
from .models import U2NET
|
||||
from .models import U2NET, SENet
|
||||
|
||||
|
||||
@MODELS.register_module(
|
||||
@@ -22,13 +22,25 @@ class SalientDetection(TorchModel):
|
||||
"""str -- model file root."""
|
||||
super().__init__(model_dir, *args, **kwargs)
|
||||
model_path = osp.join(model_dir, ModelFile.TORCH_MODEL_FILE)
|
||||
self.model = U2NET(3, 1)
|
||||
|
||||
self.norm_mean = [0.485, 0.456, 0.406]
|
||||
self.norm_std = [0.229, 0.224, 0.225]
|
||||
self.norm_size = (320, 320)
|
||||
|
||||
config_path = osp.join(model_dir, 'config.py')
|
||||
if osp.exists(config_path) is False:
|
||||
self.model = U2NET(3, 1)
|
||||
else:
|
||||
self.model = SENet(backbone_path=None, pretrained=False)
|
||||
config = Config.from_file(config_path)
|
||||
self.norm_mean = config.norm_mean
|
||||
self.norm_std = config.norm_std
|
||||
self.norm_size = config.norm_size
|
||||
checkpoint = torch.load(model_path, map_location='cpu')
|
||||
self.transform_input = transforms.Compose([
|
||||
transforms.Resize((320, 320)),
|
||||
transforms.Resize(self.norm_size),
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize(
|
||||
mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
|
||||
transforms.Normalize(mean=self.norm_mean, std=self.norm_std)
|
||||
])
|
||||
self.model.load_state_dict(checkpoint)
|
||||
self.model.eval()
|
||||
|
||||
@@ -12,6 +12,11 @@ from modelscope.utils.constant import Tasks
|
||||
|
||||
@PIPELINES.register_module(
|
||||
Tasks.semantic_segmentation, module_name=Pipelines.salient_detection)
|
||||
@PIPELINES.register_module(
|
||||
Tasks.semantic_segmentation,
|
||||
module_name=Pipelines.salient_boudary_detection)
|
||||
@PIPELINES.register_module(
|
||||
Tasks.semantic_segmentation, module_name=Pipelines.camouflaged_detection)
|
||||
class ImageSalientDetectionPipeline(Pipeline):
|
||||
|
||||
def __init__(self, model: str, **kwargs):
|
||||
|
||||
@@ -23,6 +23,27 @@ class SalientDetectionTest(unittest.TestCase, DemoCompatibilityCheck):
|
||||
import cv2
|
||||
cv2.imwrite(input_location + '_salient.jpg', result[OutputKeys.MASKS])
|
||||
|
||||
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
||||
def test_salient_boudary_detection(self):
|
||||
input_location = 'data/test/images/image_salient_detection.jpg'
|
||||
model_id = 'damo/cv_res2net_salient-detection'
|
||||
salient_detect = pipeline(Tasks.semantic_segmentation, model=model_id)
|
||||
result = salient_detect(input_location)
|
||||
import cv2
|
||||
cv2.imwrite(input_location + '_boudary_salient.jpg',
|
||||
result[OutputKeys.MASKS])
|
||||
|
||||
@unittest.skipUnless(test_level() >= 0, 'skip test in current test level')
|
||||
def test_camouflag_detection(self):
|
||||
input_location = 'data/test/images/image_camouflag_detection.jpg'
|
||||
model_id = 'damo/cv_res2net_camouflaged-detection'
|
||||
camouflag_detect = pipeline(
|
||||
Tasks.semantic_segmentation, model=model_id)
|
||||
result = camouflag_detect(input_location)
|
||||
import cv2
|
||||
cv2.imwrite(input_location + '_camouflag.jpg',
|
||||
result[OutputKeys.MASKS])
|
||||
|
||||
@unittest.skip('demo compatibility test is only enabled on a needed-basis')
|
||||
def test_demo_compatibility(self):
|
||||
self.compatibility_check()
|
||||
|
||||
Reference in New Issue
Block a user