fsted

Hello,I want to run the Prepare_2d_data,but it need scannetv2-labels.combined.tsv,where's it?

Torch version 0.3 is too old. If I use version 1.0 or above, what changes should I make？ Thanks for your code😄

Unknown timm model

7

hello,thank for the nice paper;but I want to train the model by conformer_tscam_small_patch16_224.yaml , found an error: `RuntimeError: Unknown model (conformer_ts_cam_small_patch16)` maybe the timm cannot found th model? thanks

An import error

5

hello, i got an import error: When `import inplace_abn` It tells : Traceback (most recent call last): File "", line 1, in File "/home/lib/python3.7/site-packages/inplace_abn/__init__.py", line 1, in from .abn import...

where is the path to scannetv2-labels.combined.tsv

1

Hello, i try to run prepare_2d_data but found ``` if opt.export_label_images: assert opt.label_map_file != '' ``` and it need path to scannetv2-labels.combined.tsv ,where is it? Thanks for the code

An error occurred during the test. An error was reported：cannot find "/retrieval_model/reg.pb" ， but I don't know what reg.pb is，how can I get it?

When i run the train_voc.py ,found: FileNotFoundError: [Errno 2] No such file or directory: './checkpoints/voc_512x800_loss2.0635.pth' the file has been Missed？

the compile error

2

Hi,thanks for your work,it'sgreat.But I meet a error when i try to compile it: -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-cpython-37/tree_filter_cuda.cpython-37m-x86_64-linux-gnu.so /home/share/lihaoyu/anaconda3/envs/sas/compiler_compat/ld: cannot find -lc10: not found /home/share/lihaoyu/anaconda3/envs/sas/compiler_compat/ld: cannot...

compile error

1

Hi! Thank you for your code. This is a surprising article, but I encountered a confusing compilation error when I run setup.py: /home/anaconda3/compiler_compat/ld: cannot find -lc10 /home/anaconda3/compiler_compat/ld: cannot find -ltorch...

hi,thanks for the code ,but when i try to train the MaskCLIP+, I found an error: `model= dict( type='EncoderDecoder', pretrained='open-mmlab://resnet101_v1c', backbone=dict( type='ResNetV1c', depth=101, num_stages=4, out_indices=(0, 1, 2, 3), dilations=(1, 1,...