Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error when run PVAnet_test #33

Open
autumnqin opened this issue Mar 13, 2017 · 9 comments
Open

Error when run PVAnet_test #33

autumnqin opened this issue Mar 13, 2017 · 9 comments

Comments

@autumnqin
Copy link

python dv.py --model ~/PVAnet_iter_70000.ckpt --net PVAnet_test

NotFoundError (see above for traceback): Key conv5_4/last_bn_scale/beta not found in checkpoint;

W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/alpha not found in checkpoint
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]
W tensorflow/core/framework/op_kernel.cc:993] Not found: Key conv5_4/last_bn_scale/beta not found in checkpoint
[[Node: save/RestoreV2_473 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_save/Const_0, save/RestoreV2_473/tensor_names, save/RestoreV2_473/shape_and_slices)]]

@CharlesShang
Copy link
Owner

Was it solved?
There must be a typo in the test net.
I'll run some debug in my spare time

@jwnsu
Copy link

jwnsu commented Mar 15, 2017

test error is easy to resolve, however it has very high error (mAP is below 0.1) -- caffe version is one of most accurate models. It seems conv2_1/1/conv layer is different from the paper, can also be caused by issue in pva_negation_block/v2.

@autumnqin
Copy link
Author

train is different from test, and both are different from Caffe version

@baileyqbb
Copy link

Hi, there! I faced the same issue, but finally find the errors in PVAnet_test.py. Here is the lines I've changed to make the test work:
lines to comment:
85 --> .scale(c_in=384, name='conv5_4/last_bn_scale')
118 --> (self.feed('convf_rpn', 'convf_2')
119 --> .concat(axis=3, name='convf'))

lines to change:
92 --> (self.feed('downsample', 'conv4_4', 'upsamle') ---> (self.feed('downsample', 'conv4_4')
121 --> (self.feed('convf', 'rois') ---> (self.feed('convf_2', 'rois')
122 --> .roi_pool(7, 7, 1.0/16, name='roi_pooling') ---> .roi_pool(6, 6, 1.0/16, name='roi_pooling')

Hope this will help!

BTW, as mentioned by @jwnsu, test error is quite high. I trained the model using VOC2012 data with 200000 iters, the mAP is about 0.03, which is totally unacceptable. I am gonna train the model with more iters, and meanwhile, check the PVAnet to see if it is the same with the caffe version mentioned by @autumnqin.

Will update if any news.

@sevaxyz
Copy link

sevaxyz commented May 22, 2017

@baileyqbb Haven't you figured out the issue with the low mAP by any chance?

@yshen92
Copy link

yshen92 commented Jul 28, 2017

Hi guys, can anyone please share some tips on improving the mAP?

@QueenJuliaZxx
Copy link

thank you very much @baileyqbb

@gentlebreeze1
Copy link

@baileyqbb @QueenJuliaZxx do you run pva-faster-rcnn successfully?my pva.npy seem to be wrong.where do you download?what the script command do you run ?thanks for your help

@amirmgh1375
Copy link

@baileyqbb
thank you so much 👍
it works very well 💯 🥇

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

9 participants