RuntimeError: Error(s) in loading state_dict for ConvNeXtV2:

[weihongwei-zg]

criterion = LabelSmoothingCrossEntropy()
Traceback (most recent call last):
File "main_finetune.py", line 437, in
main(args)
File "main_finetune.py", line 351, in main
optimizer=optimizer, loss_scaler=loss_scaler, model_ema=model_ema)
File "/media/wangshuang/sdb/object_class/ConvNeXt-V2/utils.py", line 495, in auto_load_model
model_without_ddp.load_state_dict(checkpoint['model'])
File "/home/wangshuang/anaconda3/envs/yolov8/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for ConvNeXtV2:
Missing key(s) in state_dict: "downsample_layers.0.0.weight",

[weihongwei-zg]

Why can we only use fine-tuning to evaluate the trained model after pre-training. And there will be errors when fine-tuning the evaluation and loading the model.

[weihongwei-zg]

python main_pretrain.py --model convnextv2_base --batch_size 8 --update_freq 8 --blr 1.5e-4 --epochs 1600 --warmup_epochs 40 --data_path /media/wangshuang/sdb/object_class/dataset --output_dir /media/wangshuang/sdb/object_class/result

python main_finetune.py --model convnextv2_base --eval true --resume /media/wangshuang/sdb/object_class/result/checkpoint-157.pth --input_size 224 --data_path /media/wangshuang/sdb/object_class/dataset

[zermatt-luo]

criterion = LabelSmoothingCrossEntropy() Traceback (most recent call last): File "main_finetune.py", line 437, in main(args) File "main_finetune.py", line 351, in main optimizer=optimizer, loss_scaler=loss_scaler, model_ema=model_ema) File "/media/wangshuang/sdb/object_class/ConvNeXt-V2/utils.py", line 495, in auto_load_model model_without_ddp.load_state_dict(checkpoint['model']) File "/home/wangshuang/anaconda3/envs/yolov8/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1224, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for ConvNeXtV2: Missing key(s) in state_dict: "downsample_layers.0.0.weight",

Hello, may I ask if you have installed MinkowskiEngine? I tried to install from online tutorials, but the two py files MinkowskiDepthwiseConvolution and MinkowskiLinear are missing, and the rest are normal. Thanks

[zermatt-luo]

Hello, may I ask if you have installed MinkowskiEngine? I tried to install from online tutorials, but the two py files MinkowskiDepthwiseConvolution and MinkowskiLinear are missing, and the rest are normal. Thanks！

[MinJunKang]

@XuLuo121 I think you have to install MinkowskiEngine with the author's provided version here : https://github.com/shwoo93/MinkowskiEngine/tree/5f459408e054933327873b29f1287275f3af6375