weixin_39608613
weixin_39608613
2021-01-01 01:42

"Cannot find argument 'out_grad'" when using train_P_net.py

Hi Seanlinx,

I run into this problem when trying to use train_P_.net


Called with argument:
Namespace(begin_epoch=0, dataset_path='data/mtcnn', end_epoch=16, epoch=0, frequent=200, gpu_ids='0', image_set='train_12', lr=0.01, prefix='model/pnet', pretrained='model/pnet', resume=False, root_path='data')
mtcnn_train_12 gt imdb loaded from data/cache/mtcnn_train_12_gt_roidb.pkl
append flipped images to imdb 1545850
Traceback (most recent call last):
  File "train_P_net.py", line 54, in <module>
    args.begin_epoch, args.end_epoch, args.frequent, args.lr, args.resume)
  File "train_P_net.py", line 13, in train_P_net
    sym = P_Net()
  File "/home/dang/test/mtcnn/core/symbol.py", line 38, in P_Net
    grad_scale=1, out_grad=True, name="bbox_pred")
  File "mxnet/cython/symbol.pyx", line 151, in symbol._make_atomic_symbol_function.creator (mxnet/cython/symbol.cpp:3591)
  File "mxnet/cython/base.pyi", line 36, in symbol.CALL (mxnet/cython/symbol.cpp:1624)
mxnet.base.MXNetError: Cannot find argument 'out_grad', Possible Arguments:
----------------
grad_scale : float, optional, default=1
    Scale the gradient by a float factor
, in operator LinearRegressionOutput(name="", out_grad="True", grad_scale="1")
</module>

I modified regression_output-inl.h according to mxnet_diff.patch (git apply mxnet_diff.patch), but the issue still appears. Could you please help me out? Thanks.

该提问来源于开源项目:Seanlinx/mtcnn

  • 点赞
  • 写回答
  • 关注问题
  • 收藏
  • 复制链接分享
  • 邀请回答

17条回答

  • weixin_39992417 weixin_39992417 4月前

    You should run make and then reinstall python package to validate the changes.

    点赞 评论 复制链接分享
  • weixin_39758041 weixin_39758041 4月前

    have you solved this problem?

    点赞 评论 复制链接分享
  • weixin_39758041 weixin_39758041 4月前

    where is the makefile ?

    点赞 评论 复制链接分享
  • weixin_39794734 weixin_39794734 4月前

    have you solve the problem?I also meet the same problem,could you please tell how to fix it?

    点赞 评论 复制链接分享
  • weixin_39955829 weixin_39955829 4月前

    someone have solve this problem?

    点赞 评论 复制链接分享
  • weixin_39737492 weixin_39737492 4月前

    someone have solve this problem?

    点赞 评论 复制链接分享
  • weixin_39984578 weixin_39984578 4月前

    have anyone solved this problem?

    点赞 评论 复制链接分享
  • weixin_39984578 weixin_39984578 4月前
    点赞 评论 复制链接分享
  • weixin_39737492 weixin_39737492 4月前

    maybe only use facenet, facenet has mtcnn inside.

    点赞 评论 复制链接分享
  • weixin_39809175 weixin_39809175 4月前

    del "out_grad" in LinearRegressionOutput()

    点赞 评论 复制链接分享
  • weixin_39554170 weixin_39554170 4月前

    have anyone solved this problem?

    点赞 评论 复制链接分享
  • weixin_39809175 weixin_39809175 4月前

    just remove it

    点赞 评论 复制链接分享
  • weixin_39554170 weixin_39554170 4月前

    Please tell me "it" is what.I can not find "it" ..thanks.

    点赞 评论 复制链接分享
  • weixin_39543835 weixin_39543835 4月前

    just remove parameter "out_grad" in SoftmaxOutput and LinearRegressionOutput

    点赞 评论 复制链接分享
  • weixin_39849418 weixin_39849418 4月前

    just remove parameter "out_grad" in SoftmaxOutput and LinearRegressionOutput

    Thanks, i'm sloved.

    点赞 评论 复制链接分享
  • weixin_39705794 weixin_39705794 4月前

    just remove it

    Why remove it?

    点赞 评论 复制链接分享
  • weixin_39700625 weixin_39700625 4月前

    Why remove it?

    点赞 评论 复制链接分享

相关推荐