RuntimeError: invalid argument 2: Input tensor must have same size as output tensor apart from the specified dimension at /opt/conda/conda

[KevinQian97]

Hello，I used your code to train. However, the model terminate after first iter Would you please help me find out the problem? Thank you Here are my Trace backs: [session 1][epoch 1][iter 0] loss: 4.0006, lr: 1.00e-02 fg/bg=(128/384), time cost: 7.218862 rpn_cls: 0.6919, rpn_box: 0.1386, rcnn_cls: 2.8319, rcnn_box 0.3382 Traceback (most recent call last): File "trainval_net.py", line 330, in roi_labels = FPN(im_data, im_info, gt_boxes, num_boxes) File "/home/zhiqi.cheng/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 357, in call result = self.forward(*input, **kwargs) File "/home/zhiqi.cheng/anaconda2/lib/python2.7/site-packages/torch/nn/parallel/data_parallel.py", line 73, in forward outputs = self.parallel_apply(replicas, inputs, kwargs) File "/home/zhiqi.cheng/anaconda2/lib/python2.7/site-packages/torch/nn/parallel/data_parallel.py", line 83, in parallel_apply return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)]) File "/home/zhiqi.cheng/anaconda2/lib/python2.7/site-packages/torch/nn/parallel/parallel_apply.py", line 67, in parallel_apply raise output RuntimeError: invalid argument 2: Input tensor must have same size as output tensor apart from the specified dimension at /opt/conda/conda-bld/pytorch_1518238409320/work/torch/lib/THC/generic/THCTensorScatterGather.cu:29

[KevinQian97]

I found that the code runs normally on faster-rcnn. But if I use the code of fpn, it failed. So I guess the problem happens in fpn.py, but I still can't find out why. What's more, I used this model to train my personal data, if I changed the data back to origin Voc2007, it works. That's strange. I just changed my personal data into the form of Voc2007. Here is one of my annotation file:

train VIRAT_S_000000.mp4_0 C:/Users/Kevin Qian/Downloads/images/train/VIRAT_S_000000.mp4_0.jpg Unknown 1920 1080 3 0

and here is the annotation file in original voc2007

VOC2007 009962.jpg The VOC2007 Database PASCAL VOC2007 flickr 246788553 Tool - Wroclaw Milosz J. 500 375 3 0

[KevinQian97]

I have solved the problem through downloading the whole pascal data set and change the data part instead of directly using my personal data. But it's interesting that I think your code is based on that of jwyang. But through using the method of changing data part, I can successfully use your code to train but that still doesn't work when it comes to jwyang's work. So, would you mind telling me if you changed some codes which is relevant to reading data from data set?

[jacco09]

I met the same problem.Could you share your solution in detail.Thanks!

[JingXiaolun]

@KevinQian97 ,I met the same problem.Could you share your solution in detail.Thanks!

[hailey94]

@KevinQian97 , I met the same problem.Could you share your solution in detail.Thanks!