Closed balescream closed 11 months ago
Do you have working resnet version yml file?
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.
how?
parameter name [conv1_1_weights] have be been used. In dygraph mode, the name of parameter can't be same.Please check the parameter attr value passed to self.create_parameter or c onstructor of dygraph Layers
same issue? how to solve?
During distillation learning using Resnet gives the following error whereas MobilenetV1Enhance works fine(Teacher +2 Students). 请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
系统环境/System Environment:CentOS Linux 7
版本号/Version:Paddle:2.3.1 PaddleOCR:2.5.0(v3) 问题相关组件/Related components:
运行指令/Command Code:CUDA_VISIBLE_DEVICES=0,1 python -m paddle.distributed.launch --gpus '0,1' tools/train.py -c /home///ppocr2.5/config_indic/hin_720_ResNet_DML_s1.yml -o Global.use_amp=True Global.scale_loss=1024.0 Global.use_dynamic_loss=true
完整报错/Complete Error Message: File "/home/ /ppocr2.5/PaddleOCR-2.5.0/tools/train.py", line 188, in
main(config, device, logger, vdl_writer)
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/tools/train.py", line 120, in main
model = build_model(config['Architecture'])
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/ppocr/modeling/architectures/init.py", line 31, in build_model
arch = getattr(mod, name)(config)
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/ppocr/modeling/architectures/distillation_model.py", line 47, in init
model = BaseModel(model_config)
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/ppocr/modeling/architectures/base_model.py", line 50, in init
self.backbone = build_backbone(config["Backbone"], model_type)
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/ppocr/modeling/backbones/init.py", line 63, in build_backbone
module_class = eval(module_name)(**config)
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/ppocr/modeling/backbones/rec_resnet_vd.py", line 200, in init
self.conv1_1 = ConvBNLayer(
File "/home/ /ppocr2.5/PaddleOCR-2.5.0/ppocr/modeling/backbones/rec_resnet_vd.py", line 43, in init
self._conv = nn.Conv2D(
File "/home//.conda/envs/spaddle/lib/python3.9/site-packages/paddle/nn/layer/conv.py", line 644, in init
super(Conv2D, self).init(
File "/home//.conda/envs/spaddle/lib/python3.9/site-packages/paddle/nn/layer/conv.py", line 133, in init
self.weight = self.create_parameter(
File "/home//.conda/envs/spaddle/lib/python3.9/site-packages/paddle/fluid/dygraph/layers.py", line 423, in create_parameter
return self._helper.create_parameter(temp_attr, shape, dtype, is_bias, File "/home//.conda/envs/spaddle/lib/python3.9/site-packages/paddle/fluid/layer_helper_base.py", line 371, in create_parameter raise ValueError( ValueError: parameter name [conv1_1_weights] have be been used. In dygraph mode, the name of parameter can't be same.Please check the parameter attr value passed to self.create_parameter or constructor of dygraph Layers