When I ran the train.py file, I encountered a problem, I hope you can answer it. Thank you.

[wry980105]

File "train.py", line 604, in
main(args)
File "train.py", line 473, in main
trainer.run(train_loader,max_epochs=args.epoch)
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/ignite/engine/engine.py", line 446, in run
self._handle_exception(e)
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/ignite/engine/engine.py", line 410, in _handle_exception
raise e
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/ignite/engine/engine.py", line 433, in run
hours, mins, secs = self._run_once_on_dataset()
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/ignite/engine/engine.py", line 399, in _run_once_on_dataset
self._handle_exception(e)
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/ignite/engine/engine.py", line 410, in _handle_exception
raise e
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/ignite/engine/engine.py", line 387, in _run_once_on_dataset
for batch in self.state.dataloader:
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next
data = self._next_data()
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 856, in _next_data
return self._process_data(data)
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 881, in _process_data
data.reraise()
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/_utils.py", line 395, in reraise
raise self.exc_type(msg)
IndexError: Caught IndexError in DataLoader worker process 3.
Original Traceback (most recent call last):
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/zhaoliuqing/wry/Graph2plan-master/Network/model/floorplan.py", line 223, in getitem
return fp.get_train_data()
File "/home/zhaoliuqing/wry/Graph2plan-master/Network/model/floorplan.py", line 202, in get_train_data
boxes = self.get_boxes(tensor=tensor)
File "/home/zhaoliuqing/wry/Graph2plan-master/Network/model/floorplan.py", line 159, in get_boxes
boxes = np.apply_along_axis(norm,1,boxes)
File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/numpy/lib/shape_base.py", line 380, in apply_along_axis
res = asanyarray(func1d(inarr_view[ind0], *args, **kwargs))
File "/home/zhaoliuqing/wry/Graph2plan-master/Network/model/floorplan.py", line 158, in
norm = lambda box:np.array([X[box[1]],Y[box[0]],X[box[3]-1],Y[box[2]-1]])
IndexError: index 208 is out of bounds for axis 0 with size 208

[zzilch]

Can you provide the name of the error data item? You can print it at here

[wry980105]

Thank you for your reply!
It is this mistake that has occurred：“norm = lambda box:np.array([X[box[1]],Y[box[0]],X[box[3]-1],Y[box[2]-1]])
IndexError: index 208 is out of bounds for axis 0 with size 208”.I read the data_item，it maybe the gtBoxNew has problem.But i am not sure and don't know how to handle it.Could you please give me some methods?

[zzilch]

Yeah, I think there is something wrong with the training data. I need you to print the name of the wrong data.
In the class FloorPlanDataset , it will call get_train_data to get the traininng data of a Floorplan.
And in get_train_data, it will call get_boxes which casued the error you encountered.
You can print the name before it calls get_boxes in the line 193 of floorplan.py.
If you provide the name of the problem data, I can figure out what happened.

[wry980105]

I print the data.name as you said. The data that went wrong was this one up here The box name that went wrong was this one up here. But I ran it the second time and  this data was wrong. Each time I ran it,  the wrong data was different. It's so stange that I don't know what is wrong.

…

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "HanHan55/Graph2plan" <notifications@github.com&gt;; 发送时间:&nbsp;2020年10月18日(星期天) 凌晨0:13 收件人:&nbsp;"HanHan55/Graph2plan"<Graph2plan@noreply.github.com&gt;; 抄送:&nbsp;"瑩*瑩"<1151735452@qq.com&gt;;"Comment"<comment@noreply.github.com&gt;; 主题:&nbsp;Re: [HanHan55/Graph2plan] When I ran the train.py file, I encountered a problem, I hope you can answer it. Thank you. (#7) Yeah, I think there is something wrong with the training data. I need you to print the name of the wrong data. In the class FloorPlanDataset , it will call get_train_data to get the traininng data of a Floorplan. And in get_train_data, it will call get_boxes which casued the error you encountered. You can print the name before it calls get_boxes in the line 193 of floorplan.py. If you provide the name of the problem data, I can figure out what happened. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[zzilch]

Sorry, did you paste any images? I cannot see anyone of them.

[wry980105]

I print the data.name as you said. “&nbsp; &nbsp; &nbsp; &nbsp;def get_train_data(self, tensor=True): &nbsp; &nbsp; &nbsp; &nbsp; name = self.data.name &nbsp; &nbsp; &nbsp; &nbsp; print("____________________") &nbsp; &nbsp; &nbsp; &nbsp; print(name)&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp;” “&nbsp;17678

…

____________________" The data that went wrong was this one up here” “tensor([[0.8256, 0.7801, 0.3333, 0.4277], &nbsp; &nbsp; &nbsp; &nbsp; [0.8953, 0.4608, 0.1938, 0.1988], &nbsp; &nbsp; &nbsp; &nbsp; [0.8140, 0.2199, 0.3566, 0.2711], &nbsp; &nbsp; &nbsp; &nbsp; [0.0930, 0.2861, 0.1705, 0.2590], &nbsp; &nbsp; &nbsp; &nbsp; [0.4264, 0.3404, 0.7132, 0.6807]])” The box name that went wrong was this one up here. "44257

____________________" “3744

_________________” But I ran it the second time and&nbsp; this data was wrong. Each time I ran it,&nbsp; the&nbsp;wrong&nbsp;data was different. It's so stange that I don't know what is wrong. In addition，may&nbsp;I&nbsp;ask&nbsp;if we can add a WeChat?We can talk conveniently.My number is 13750854386,thank you!

------------------&nbsp;原始邮件&nbsp;------------------ 发件人: "HanHan55/Graph2plan" <notifications@github.com&gt;; 发送时间:&nbsp;2020年10月19日(星期一) 上午8:23 收件人:&nbsp;"HanHan55/Graph2plan"<Graph2plan@noreply.github.com&gt;; 抄送:&nbsp;"瑩*瑩"<1151735452@qq.com&gt;;"Comment"<comment@noreply.github.com&gt;; 主题:&nbsp;Re: [HanHan55/Graph2plan] When I ran the train.py file, I encountered a problem, I hope you can answer it. Thank you. (#7) Sorry, did you paste any images? I cannot see anyone of them. — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[LucaJeevanjee]

Hello, I am receiving this issue as well,
The index in which the error occurs changes when the batch size and number of workers is changed.

This is the log from when it crashes.
Looks like either training data: 27184 or 75591
Thanks in advance!