python - 在 3d-pose-baseline 中找不到模型错误
问题描述
我试图使用3d-pose-baseline将 2d 关键点转换为 3d，但是当我使用以下命令运行预训练模型时
python src/predict_3dpose.py --camera_frame --residual --batch_norm --dropout 0.5 --max_norm --evaluateActionWise --use_sh --epochs 200 --sample --load 4874200
我收到以下错误：
NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the
checkpoint. Original error:
NewRandomAccessFile failed to Create/Open: experiments\All\dropout_0.5\epochs_200\lr_0.001\residual\depth_2\linear_size1024\batch_size_64\no_procrustes\maxnorm\batch_normalization\use_stacked_hourglass\predict_17\checkpoint-4874200.data-00000-of-00001 : The system cannot find the path specified.
; No such process
[[node save/RestoreV2 (defined at D:\Programming\PoseNet\tf-pose-estimation\3d-pose-baseline\src\linear_model.py:151) ]]
我已经下载了预训练模型，并且错误声称不存在的路径确实存在于我的系统中。
问题可能出在哪里以及如何解决？我什至尝试像在提到的存储库中那样重新训练模型，但它在每 100 个批次后无法写入检查点，最后在 1 个 epoch 后它显示与上述相同的错误。