PaddleSlim icon indicating copy to clipboard operation
PaddleSlim copied to clipboard

PaddleSlim is an open-source library for deep model compression and architecture search.

Results 231 PaddleSlim issues
Sort by recently updated
recently updated
newest added

按照离线动态量化教程https://paddle-inference.readthedocs.io/en/latest/guides/x86_cpu_infer/paddle_x86_cpu_int8.html#id1 ,用quant_post_static保存量化模型,再用脚本转成int8模型。教程里的paddle.models.mobilenetv1没有问题,量化、部署都ok,但是换UNet就会在inference推理时报错(转int8始终没有问题),看起来是和concat有关。 ``` InvalidArgumentError: Tensor holds the wrong type, it holds int8_t, but desires to be uint8_t. [Hint: Expected valid == true, but received valid:0 != true:1.] (at /home/wangye19/Paddle/paddle/fluid/framework/tensor_impl.h:33) [operator...

C:\Users\1\anaconda3\envs\paddle_env\lib\site-packages\paddle\tensor\creation.py:125: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warni ng, use `object` by itself. Doing this will not modify any behavior and is safe....

环境:AIStudio GPU 模型结构:使用PaddleNLP/examples/information_extraction/waybill_ie模型,模型结构是ernie+crf。 当前使用AutoCompression。 问题:目前模型为静态图,最后一层为crf层,模型预测时走维特比算法,无法输入标签,无法计算loss,请问这个需要怎么处理呢?

FirstRunCrashedException: First run crashed, abort. Please check your setup -- we assume that your default configuration does not crashes. (To deactivate this exception, use the SMAC scenario option 'abort_on_first_run_crash'). Additional...

使用如下命令进行自动压缩时出现错误: ``` %cd /home/aistudio/work/PaddleSlim-develop/ !python demo/auto_compression/detection/run.py --config_path=demo/auto_compression/detection//configs/ppyoloe_l_qat_dist.yaml --eval=True ``` 报错为: ``` /home/aistudio/work/PaddleSlim-develop /opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:130: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by...

fixbugs in static training ,lr_sheduler should be maintained after quant

Hi, 请问下, paddle slim tinypose 量化训练版本何时能够release啊? 或者已经在主干了吗?多谢 BR

报错信息: ValueError: (InvalidArgument) Currently, Tensor.__indices__() only allows indexing by Integers, Slices, Ellipsis, None, tuples of these types and list of Bool and Integers, but received str in 1th slice item...