zifuwan / Sigma

[WACV 2025] Python implementation of Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation
https://zifuwan.github.io/Sigma/
MIT License
190 stars 19 forks source link

Question about eval: #35

Closed donggaomu closed 1 month ago

donggaomu commented 1 month ago

While running the eval.py file, I encountered the following error while loading the training weights: Traceback (most recent call last): File "eval.py", line 125, in _, mean_IoU = segmentor.run_eval(config.checkpoint_dir, args.epochs, config.val_log_file, File "/root/autodl-tmp/Sigma-main/engine/evaluator.py", line 151, in run_eval self.val_func = load_model(self.network, model) File "/root/autodl-tmp/Sigma-main/utils/pyt_utils.py", line 181, in load_model model.load_state_dict(state_dict, strict=True) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 2041, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for EncoderDecoder: Missing key(s) in state_dict: "backbone.cross_mamba.0.op.in_proj.weight", "backbone.cross_mamba.0.op.in_proj_modalx.weight", "backbone.cross_mamba.0.op.conv2d.weight", "backbone.cross_mamba.0.op.conv2d.bias", "backbone.cross_mamba.0.op.out_proj_rgb.weight", "backbone.cross_mamba.0.op.out_proj_e.weight", "backbone.cross_mamba.0.op.CMA_ssm.A_log_1", "backbone.cross_mamba.0.op.CMA_ssm.A_log_2", "backbone.cross_mamba.0.op.CMA_ssm.D_1", "backbone.cross_mamba.0.op.CMA_ssm.D_2", "backbone.cross_mamba.0.op.CMA_ssm.x_proj_1.weight", "backbone.cross_mamba.0.op.CMA_ssm.x_proj_2.weight", "backbone.cross_mamba.0.op.CMA_ssm.dt_proj_1.weight", "backbone.cross_mamba.0.op.CMA_ssm.dt_proj_1.bias", "backbone.cross_mamba.0.op.CMA_ssm.dt_proj_2.weight", "backbone.cross_mamba.0.op.CMA_ssm.dt_proj_2.bias", "backbone.cross_mamba.0.op.CMA_ssm.....