Skip to content

使用multilabelseg训练后并export的模型应该如何使用PaddleSlim自动压缩? #3926

@hp0716

Description

@hp0716

问题确认 Search before asking

  • 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer.

请提出你的问题 Please ask your question

使用multilabelseg训练得到的模型输出为[1,6,540,856](NCHW),使用act压缩工具并沿用pp_mobileseg的config发现输出结果少了的C这个维度,在验证时会出现报错,请问现在是否支持multilabelseg的蒸馏压缩?配置文件该如何修改?
报错如下:

Image 使用的paddle版本如下 Image 目前使用的act配置文件如下

`Global:
model_dir: /data/code/idcard/api/quality/v6/PaddleSeg/output/pp_mobileseg_idcard_256x256_80k_withaux0715/inference_model_quant
model_filename: model.pdmodel
params_filename: model.pdiparams

Distillation:
alpha: 1.0
loss: l2
node:
- conv2d_75.tmp_0 # change to the name of the output of the last conv in the model.pdmodel in netron

QuantAware:
onnx_format: False
quantize_op_types:
- conv2d
- depthwise_conv2d

TrainConfig:
epochs: 20
eval_iter: 100
learning_rate: 0.0005
optimizer_builder:
optimizer:
type: SGD
weight_decay: 4.0e-05
`

Metadata

Metadata

Assignees

Labels

questionFurther information is requested

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions