run the demo, where to download the file "vgg16_faster_rcnn_iter_70000.ckpt" about faster-rcnn-tensorflow-python3

[dBeker]

Please check instruction number 6. There are links to download required precompiled binaries.

[WANGYong-NJ]

Thank you！
I have download the file, and change its name to "vgg16_faster_rcnn_iter_70000.ckpt.meta", but the error still happens.

[dBeker]

Oh ok. I will take a look to it at weekend and try to let you know about the issue.

[zhanglsky]

Hi,I have meet the same problems,Did this problem fixed?

[1hyx]

(py35) E:\Git_code\Faster-RCNN-TensorFlow-Python3.5-master>python demo.py
output\res101\voc_2007_trainval+voc_2012_trainval\default\res101_faster_rcnn_iter_110000.ckpt
Traceback (most recent call last):
File "demo.py", line 127, in
'our server and place them properly?').format(tfmodel + '.meta'))
OSError: output\res101\voc_2007_trainval+voc_2012_trainval\default\res101_faster_rcnn_iter_110000.ckpt.meta not found.
Did you download the proper networks from our server and place them properly?

And I think this error means that the \Faster-RCNN-TensorFlow-Python3.5-master\default\voc_2007_trainval\default........(What I download about this folder is empty)
I think this is not the problem of step6.

[zhanglsky]

Hi，I did not download the .meta file. I tried a lot of ways, and find My problem is that " Tensor name "XXXX" not found in checkpoint files".and each time I tried, the error's 'tensor name' not same.

[gokulkrshna]

Same problem has been encountered,can you please check the demo.py file and update

[dBeker]

Can you just please download all files required for it? You need .ckpt and .ckpt.meta together. Please be aware that I have not trained this network as stated in readme file. So, I don't have the most up-to-date weights. Please refer to links given in readme. Also, they may have updated the model as well as weights. Please feel free to modify the branch if you can find a solution.

[meanqqq]

@1hyx Hi,I have met the same problems. Do you know where to download to the folder required?Did this problem fixed?

[shyern]

when i trained the model, this problem happened:

d:\tf_rcnn\lib\layer_utils\proposal_target_layer.py(139)_sample_rois()
-> keep_inds = np.append(fg_inds, bg_inds)
(Pdb)
(Pdb)
(Pdb)
...

and the program is paused and to do nothing, i don't know what happened and what should i do?