Traceback (most recent call last):
File "run.py", line 384, in <module>
main()
File "run.py", line 377, in main
ac.compress()
File "/root/.conda/envs/lzx/lib/python3.8/site-packages/paddleslim/auto_compression/compressor.py", line 586, in compress
self.single_strategy_compress(strategy, config, strategy_idx,
File "/root/.conda/envs/lzx/lib/python3.8/site-packages/paddleslim/auto_compression/compressor.py", line 753, in single_strategy_compress
metric = self.eval_function(self._exe, inference_program,
File "run.py", line 278, in eval_function
res = metric.accumulate()
File "/root/.conda/envs/lzx/lib/python3.8/site-packages/paddlenlp/metrics/glue.py", line 371, in accumulate
preds = [item for sublist in self.preds for item in sublist]
File "/root/.conda/envs/lzx/lib/python3.8/site-packages/paddlenlp/metrics/glue.py", line 371, in <listcomp>
preds = [item for sublist in self.preds for item in sublist]
TypeError: 'float' object is not iterable
软件环境
重复问题
错误描述
稳定复现步骤 & 代码
https://github.com/PaddlePaddle/PaddleSlim/tree/develop/example/auto_compression/pytorch_huggingface 在使用PaddleSlim,进行自动压缩时,python run.py --config_path=./config/stsb.yaml --save_dir='./output/stsb' stsb.yaml,改成了 只有这个,失败了