执行超参数搜索时KeyError报错

[ithok]

ERROR:hyperopt.fmin:job exception: 'model'

0%| | 0/12 [1:01:04<?, ?trial/s, best loss=?]
Traceback (most recent call last):
File "run_hyper.py", line 26, in
main()
File "run_hyper.py", line 18, in main
hp.run()
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/recbole/trainer/hyper_tuning.py", line 411, in run
fmin(
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/hyperopt/fmin.py", line 553, in fmin
rval.exhaust()
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/hyperopt/fmin.py", line 356, in exhaust
self.run(self.max_evals - n_done, block_until_done=self.asynchronous)
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/hyperopt/fmin.py", line 292, in run
self.serial_evaluate()
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/hyperopt/fmin.py", line 170, in serial_evaluate
result = self.domain.evaluate(spec, ctrl)
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/hyperopt/base.py", line 907, in evaluate
rval = self.fn(pyll_rval)
File "/opt/conda/envs/siton_env/lib/python3.8/site-packages/recbole/trainer/hyper_tuning.py", line 349, in trial
result_dict["model"],
KeyError: 'model'

RT，报错信息如上，跑的模型是Hmlet，输入指令如下:

python run_hyper.py --model='HMLET' --dataset='ml-1m' --config_files='ml-1m.yaml' --params_file=Hmlet.hyper

[hyp1231]

请问您的 recbole 版本是？我在 recbole 1.0.1 和 1.1.1 都进行了测试，似乎没有复现您说的问题。

[ithok]

Name Version Build Channel

_libgcc_mutex 0.1 main
_openmp_mutex 5.1 1_gnu
absl-py 1.4.0 pypi_0 pypi
ca-certificates 2023.01.10 h06a4308_0
cachetools 5.3.0 pypi_0 pypi
certifi 2022.12.7 py38h06a4308_0
charset-normalizer 2.1.1 pypi_0 pypi
cloudpickle 2.2.1 pypi_0 pypi
cmake 3.25.0 pypi_0 pypi
colorama 0.4.4 pypi_0 pypi
colorlog 4.7.2 pypi_0 pypi
filelock 3.9.0 pypi_0 pypi
future 0.18.3 pypi_0 pypi
google-auth 2.16.2 pypi_0 pypi
google-auth-oauthlib 0.4.6 pypi_0 pypi
grpcio 1.51.3 pypi_0 pypi
hyperopt 0.2.5 pypi_0 pypi
idna 3.4 pypi_0 pypi
importlib-metadata 6.1.0 pypi_0 pypi
jinja2 3.1.2 pypi_0 pypi
joblib 1.2.0 pypi_0 pypi
ld_impl_linux-64 2.38 h1181459_1
libffi 3.4.2 h6a678d5_6
libgcc-ng 11.2.0 h1234567_1
libgomp 11.2.0 h1234567_1
libstdcxx-ng 11.2.0 h1234567_1
lit 15.0.7 pypi_0 pypi
markdown 3.4.1 pypi_0 pypi
markupsafe 2.1.2 pypi_0 pypi
mpmath 1.2.1 pypi_0 pypi
ncurses 6.4 h6a678d5_0
networkx 3.0 pypi_0 pypi
numpy 1.23.5 pypi_0 pypi
oauthlib 3.2.2 pypi_0 pypi
openssl 1.1.1t h7f8727e_0
pandas 1.5.3 pypi_0 pypi
pillow 9.3.0 pypi_0 pypi
pip 23.0.1 py38h06a4308_0
plotly 5.13.1 pypi_0 pypi
protobuf 4.22.1 pypi_0 pypi
psutil 5.9.4 pypi_0 pypi
py4j 0.10.9.7 pypi_0 pypi
pyasn1 0.4.8 pypi_0 pypi
pyasn1-modules 0.2.8 pypi_0 pypi
pyg-lib 0.2.0+pt20cu117 pypi_0 pypi
pyparsing 3.0.9 pypi_0 pypi
python 3.8.16 h7a1cb2a_3
python-dateutil 2.8.2 pypi_0 pypi
pytz 2022.7.1 pypi_0 pypi
pyyaml 6.0 pypi_0 pypi
readline 8.2 h5eee18b_0
recbole 1.1.1 pypi_0 pypi
requests 2.28.1 pypi_0 pypi
requests-oauthlib 1.3.1 pypi_0 pypi
rsa 4.9 pypi_0 pypi
scikit-learn 1.2.2 pypi_0 pypi
scipy 1.10.1 pypi_0 pypi
setuptools 65.6.3 py38h06a4308_0
six 1.16.0 pypi_0 pypi
sqlite 3.41.1 h5eee18b_0
sympy 1.11.1 pypi_0 pypi
tabulate 0.9.0 pypi_0 pypi
tenacity 8.2.2 pypi_0 pypi
tensorboard 2.12.0 pypi_0 pypi
tensorboard-data-server 0.7.0 pypi_0 pypi
tensorboard-plugin-wit 1.8.1 pypi_0 pypi
thop 0.1.1-2209072238 pypi_0 pypi
threadpoolctl 3.1.0 pypi_0 pypi
tk 8.6.12 h1ccaba5_0
torch 2.0.0+cu117 pypi_0 pypi
torch-cluster 1.6.1+pt20cu117 pypi_0 pypi
torch-geometric 2.2.0 pypi_0 pypi
torch-scatter 2.1.1+pt20cu117 pypi_0 pypi
torch-sparse 0.6.17+pt20cu117 pypi_0 pypi
torch-spline-conv 1.2.2+pt20cu117 pypi_0 pypi
torchaudio 2.0.1+cu117 pypi_0 pypi
torchvision 0.15.1+cu117 pypi_0 pypi
tqdm 4.65.0 pypi_0 pypi
triton 2.0.0 pypi_0 pypi
typing-extensions 4.4.0 pypi_0 pypi
urllib3 1.26.13 pypi_0 pypi
werkzeug 2.2.3 pypi_0 pypi
wheel 0.38.4 py38h06a4308_0
xz 5.2.10 h5eee18b_1
zipp 3.15.0 pypi_0 pypi
zlib 1.2.13 h5eee18b_0

您好，是1.1.1版本的 condalist如上

[ithok]

看起来像是hyperopt的问题

[ithok]

您好，可以提供一下您运行的hyperopt的版本吗

[hyp1231]

您好！目前初步判定是我们对 RecBole 1.1.1 版本适配产生的 bug。

bug 产生原因：
RecBole 1.1.1 的某个 commit 里给超参调优的目标函数中加入了新的返回值

RUCAIBox/RecBole@05a223e#diff-fe46181d8ec96ec5c6e9b1edd0dd0af2b8e4f8b4cab6a7e5a2090ef8a34f20eeL334-R347

但是 RecBole-GNN 的超参调优的目标函数并没有返回 'model' 这个 key

RecBole-GNN/recbole_gnn/quick_start.py

Lines 82 to 87 in 77d76b9

	return {
	'best_valid_score': best_valid_score,
	'valid_score_bigger': config['valid_metric_bigger'],
	'best_valid_result': best_valid_result,
	'test_result': test_result
	}

您如果着急的话可以先给 recbole_gnn/quick_start.py 的 82 行附近的返回值中加入一个新 key 值：

return {
  'model': config['model'],
  # ... ...
}

我们也将马上修复并进行测试，感谢找到这个 bug！！

[ithok]

好的，非常感谢！