推理报错 NameError: name 'model_dir' is not defined

感谢您的错误报告，我们非常感谢。

检查清单

我已搜索相关问题，但无法获得预期的帮助。
最新版本中尚未修复此错误。

运行出错：

python app/hydit_app.py

flash_attn import failed: No module named 'flash_attn'
2024-06-14 12:21:58.616 | INFO     | hydit.inference:__init__:160 - Got text-to-image model root path: ckpts/t2i
2024-06-14 12:21:58.628 | INFO     | hydit.inference:__init__:169 - Loading CLIP Text Encoder...
2024-06-14 12:22:01.049 | INFO     | hydit.inference:__init__:172 - Loading CLIP Text Encoder finished
2024-06-14 12:22:01.049 | INFO     | hydit.inference:__init__:175 - Loading CLIP Tokenizer...
2024-06-14 12:22:01.085 | INFO     | hydit.inference:__init__:178 - Loading CLIP Tokenizer finished
2024-06-14 12:22:01.085 | INFO     | hydit.inference:__init__:181 - Loading T5 Text Encoder and T5 Tokenizer...
You are using the default legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565
/home/swoole/anaconda3/envs/HunyuanDiT/lib/python3.8/site-packages/transformers/convert_slow_tokenizer.py:550: UserWarning: The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option which is not implemented in the fast tokenizers. In practice this means that the fast version of the tokenizer can produce unknown tokens whereas the sentencepiece version would have converted these unknown tokens into a sequence of byte tokens matching the original piece of text.
  warnings.warn(
You are using a model of type mt5 to instantiate a model of type t5. This is not supported for all configurations of models and can yield errors.
2024-06-14 12:22:15.378 | INFO     | hydit.inference:__init__:185 - Loading t5_text_encoder and t5_tokenizer finished
2024-06-14 12:22:15.378 | INFO     | hydit.inference:__init__:188 - Loading VAE...
2024-06-14 12:22:15.473 | INFO     | hydit.inference:__init__:191 - Loading VAE finished
2024-06-14 12:22:15.473 | INFO     | hydit.inference:__init__:195 - Building HunYuan-DiT model...
Traceback (most recent call last):
  File "app/hydit_app.py", line 26, in <module>
    args, gen, enhancer = inferencer()
  File "/home/swoole/workspace/HunyuanDiT/./sample_t2i.py", line 17, in inferencer
    gen = End2End(args, models_root_path)
  File "/home/swoole/workspace/HunyuanDiT/./hydit/inference.py", line 205, in __init__
    model_path = model_dir / f"pytorch_model_{self.args.load_key}.pt"
NameError: name 'model_dir' is not defined

重现步骤

您运行了什么命令或脚本？

python app/hydit_app.py

您是否对代码或配置进行了任何修改？您是否理解您所修改的内容？没有任何修改
您使用了什么数据集？无

环境

请运行 python utils/collect_env.py 收集必要的环境信息并粘贴在此。

python utils/collect_env.py sys.platform: linux Python: 3.8.12 (default, Oct 12 2021, 13:49:34) [GCC 7.5.0] CUDA available: True MUSA available: False numpy_random_seed: 2147483648 GPU 0: NVIDIA GeForce RTX 4090 CUDA_HOME: None GCC: gcc (Ubuntu 12.3.0-1ubuntu1~22.04) 12.3.0 PyTorch: 1.13.1 PyTorch compiling details: PyTorch built with:

GCC 9.3
C++ Version: 201402
Intel(R) oneAPI Math Kernel Library Version 2022.1-Product Build 20220311 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
OpenMP 201511 (a.k.a. OpenMP 4.5)
LAPACK is enabled (usually provided by MKL)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.7
NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
CuDNN 8.5
Magma 2.6.1
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.13.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

TorchVision: 0.14.1+cu117


3. 您可以添加其他有助于定位问题的信息，例如
   - 您如何安装的 PyTorch \[例如，pip, conda, source\]
   - 其他可能相关的环境变量 (例如 `$PATH`, `$LD_LIBRARY_PATH`, `$PYTHONPATH` 等)

**错误回溯**

如可以，请在此粘贴错误回溯信息。

```none
回溯信息的占位符。

Bug修复

如果您已经确定了原因，可以在此提供信息。如果您愿意创建 PR 进行修复，也请在此留言，我们将不胜感激！

Tencent / HunyuanDiT

推理报错 NameError: name 'model_dir' is not defined #86