测试问题

[Whitefoxface]

当我训练完Semi-Mamba-UNet想要测试的时候，遇到了些问题：
1、python test_2D_fully.py --root_path ../data/ACDC --exp ACDC/Semi_Mamba_UNet --model mambaunet --num_classes 4 --labeled_num 3
=> merge config from ../code/configs/swin_tiny_patch4_window7_224_lite.yaml
../model/ACDC/Semi_Mamba_UNet_3/mambaunet/mambaunet_best_model.pth
Traceback (most recent call last):
File "test_2D_fully.py", line 124, in
metric = Inference(FLAGS)
File "test_2D_fully.py", line 104, in Inference
net.load_state_dict(torch.load(save_mode_path))
AttributeError: 'NoneType' object has no attribute 'load_state_dict'
于是我做出了如下改动：
在net_factory中添加：from networks.vision_mamba import MambaUnet as ViM_seg
elif net_type == "mambaunet" or net_type == "vimmamba":
net = ViM_seg(config,img_size=args.patch_size,num_classes=class_num).cuda()
然后就遇到了第二个问题：
2、python test_2D_fully.py --root_path ../data/ACDC --exp ACDC/Semi_Mamba_UNet --model mambaunet --num_classes 4 --labeled_num 3
=> merge config from ../code/configs/swin_tiny_patch4_window7_224_lite.yaml
Traceback (most recent call last):
File "test_2D_fully.py", line 124, in
metric = Inference(FLAGS)
File "test_2D_fully.py", line 99, in Inference
net = net_factory(net_type=FLAGS.model, in_chns=1,
File "/home/pdl/wb/Mamba-UNet-main/code/networks/net_factory.py", line 94, in net_factory
net = ViM_seg(config,img_size=args.patch_size,num_classes=class_num).cuda()
File "/home/pdl/wb/Mamba-UNet-main/code/networks/vision_mamba.py", line 31, in init
patch_size=config.MODEL.VSSM.PATCH_SIZE,
File "/home/pdl/anaconda3/envs/vmunet/lib/python3.8/site-packages/yacs/config.py", line 141, in getattr
raise AttributeError(name)
AttributeError: VSSM
请求大佬的帮助

[ZhangyiyiT]

你好 你的问题解决了嘛？我也遇到同样的问题

[apellidole]

这是我遇到的问题：
/Mamba-UNet-main/code# python test_2D_fully.py \

--root_path ../data/ACDC
--exp ACDC/VIM_140_labeled
--model mambaunet
--labeled_num 140
/hy-tmp/Mamba-UNet-main/code/test_2D_fully.py:12: DeprecationWarning: Please import zoom from the scipy.ndimage namespace; the scipy.ndimage.interpolation namespace is deprecated and will be removed in SciPy 2.0.0.
from scipy.ndimage.interpolation import zoom
=> merge config from ../code/configs/swin_tiny_patch4_window7_224_lite.yaml
Traceback (most recent call last):
File "/hy-tmp/Mamba-UNet-main/code/test_2D_fully.py", line 124, in
metric = Inference(FLAGS)
File "/hy-tmp/Mamba-UNet-main/code/test_2D_fully.py", line 99, in Inference
net = net_factory(net_type=FLAGS.model, in_chns=1,
File "/hy-tmp/Mamba-UNet-main/code/networks/net_factory.py", line 97, in net_factory
net = VIM_seg(config, img_size=args.patch_size,num_classes=args.num_classes).cuda()
File "/hy-tmp/Mamba-UNet-main/code/networks/vision_mamba.py", line 31, in init
patch_size=config.MODEL.VSSM.PATCH_SIZE,
File "/usr/local/miniconda3/envs/vmamba/lib/python3.10/site-packages/yacs/config.py", line 141, in getattr
raise AttributeError(name)
AttributeError: VSSM

然后我把train_fully_supervised_2D_VIM.py参数配置加到了test中
在test_2D_fully.py中对Inference(FLAGS)进行修改
args = parser.parse_args()
if FLAGS.model == "mambaunet":
config = get_config(args)
net = VIM_seg(config, img_size=FLAGS.patch_size, num_classes=FLAGS.num_classes).cuda()
else:
net = net_factory(net_type=FLAGS.model, in_chns=1, class_num=FLAGS.num_classes)

最后是成功运行了 但不知道是否正确

[Whitefoxface]

你好 你的问题解决了嘛？我也遇到同样的问题

不好意思 尚没有解决

[Whitefoxface]

这是我遇到的问题： /Mamba-UNet-main/code# python test_2D_fully.py \

--root_path ../data/ACDC --exp ACDC/VIM_140_labeled --model mambaunet --labeled_num 140 /hy-tmp/Mamba-UNet-main/code/test_2D_fully.py:12: DeprecationWarning: Please import zoom from the scipy.ndimage namespace; the scipy.ndimage.interpolation namespace is deprecated and will be removed in SciPy 2.0.0. from scipy.ndimage.interpolation import zoom => merge config from ../code/configs/swin_tiny_patch4_window7_224_lite.yaml Traceback (most recent call last): File "/hy-tmp/Mamba-UNet-main/code/test_2D_fully.py", line 124, in metric = Inference(FLAGS) File "/hy-tmp/Mamba-UNet-main/code/test_2D_fully.py", line 99, in Inference net = net_factory(net_type=FLAGS.model, in_chns=1, File "/hy-tmp/Mamba-UNet-main/code/networks/net_factory.py", line 97, in net_factory net = VIM_seg(config, img_size=args.patch_size,num_classes=args.num_classes).cuda() File "/hy-tmp/Mamba-UNet-main/code/networks/vision_mamba.py", line 31, in init patch_size=config.MODEL.VSSM.PATCH_SIZE, File "/usr/local/miniconda3/envs/vmamba/lib/python3.10/site-packages/yacs/config.py", line 141, in getattr raise AttributeError(name) AttributeError: VSSM

然后我把train_fully_supervised_2D_VIM.py参数配置加到了test中 在test_2D_fully.py中对Inference(FLAGS)进行修改 args = parser.parse_args() if FLAGS.model == "mambaunet": config = get_config(args) net = VIM_seg(config, img_size=FLAGS.patch_size, num_classes=FLAGS.num_classes).cuda() else: net = net_factory(net_type=FLAGS.model, in_chns=1, class_num=FLAGS.num_classes)

最后是成功运行了 但不知道是否正确

您好，请问下这个config = get_config(args)该怎么定义

[apellidole]

test_2D_fully.py中加上from config import get_config