Mr_Liu

in your code,the unsup data is from train dataset,[here](https://github.com/google-research/uda/blob/960684e363251772a5938451d4d2bc0f1da9e24b/text/preprocess.py#L431)

How to prepare cityscapes data

1

How to prepare cityscapes data

compile environment error

1

when i run command bash install_scripts.sh, I get the following error messages: Compiling resample2d kernels by nvcc... rm: 无法删除"Resample2d_kernel.o": 没有那个文件或目录 rm: 无法删除"../_ext": 没有那个文件或目录 In file included from /home/c201/anaconda3/envs/flow/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THVector.h:5:0, from /home/c201/anaconda3/envs/flow/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/TH.h:12,...

loss is nan

1

loc_loss: -9223372036854775808.000 | cls_loss: 9223372036854775808.000 | train_loss: inf | avg_loss: inf loc_loss: -9223372036854775808.000 | cls_loss: -9223372036854775808.000 | train_loss: nan | avg_loss: nan loc_loss: -9223372036854775808.000 | cls_loss: -9223372036854775808.000 | train_loss: nan...

How to pre-train some parameters of deep prompt？

1

How to pre-train some parameters of deep prompt？ ` Pre-train deep prompts One is to pre-train deep prompts with a vanilla PLM. Later we initialize a DPT-based retriever using the...