Train error

[fengzifrank]

An error occurred during training Can you show your dataset tree directory? Thank you (the following is my structure according to the document)
---CornerNet-Lite
------data
----------coco
---------------images
---------------------trainval2014
---------------------------------train2014.zip
---------------------minival2014
---------------------------------val2014.zip
---------------------testdev2017
---------------------------------test2017.zip

run python train.py CornerNet_Saccade --workers=1

File "train.py", line 55, in prefetch_data
data, ind = sample_data(system_config, db, ind, data_aug=data_aug)
File "/test/CornerNet-Lite/core/sample/init.py", line 5, in data_sampling_func
return globals()[sys_configs.sampling_function](sys_configs, db, k_ind, data_aug, debug)
File "/test/CornerNet-Lite/core/sample/cornernet_saccade.py", line 169, in cornernet_saccade
border = [0, image.shape[0], 0, image.shape[1]]
AttributeError: 'NoneType' object has no attribute 'shape'
Process Process-1:
Traceback (most recent call last):
File "/opt/conda/envs/CornerNet_Lite/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/opt/conda/envs/CornerNet_Lite/lib/python3.7/multiprocessing/process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "train.py", line 59, in prefetch_data
raise e
File "train.py", line 55, in prefetch_data
data, ind = sample_data(system_config, db, ind, data_aug=data_aug)
File "/test/CornerNet-Lite/core/sample/init.py", line 5, in data_sampling_func
return globals()[sys_configs.sampling_function](sys_configs, db, k_ind, data_aug, debug)
File "/test/CornerNet-Lite/core/sample/cornernet_saccade.py", line 169, in cornernet_saccade
border = [0, image.shape[0], 0, image.shape[1]]
AttributeError: 'NoneType' object has no attribute 'shape'
setting learning rate to: 0.00025
training start...
start prefetching data...
shuffling indices...
Traceback (most recent call last):
File "train.py", line 55, in prefetch_data
data, ind = sample_data(system_config, db, ind, data_aug=data_aug)
File "/test/CornerNet-Lite/core/sample/init.py", line 5, in data_sampling_func
return globals()[sys_configs.sampling_function](sys_configs, db, k_ind, data_aug, debug)
File "/test/CornerNet-Lite/core/sample/cornernet_saccade.py", line 169, in cornernet_saccade
border = [0, image.shape[0], 0, image.shape[1]]
AttributeError: 'NoneType' object has no attribute 'shape'
Process Process-2:
Traceback (most recent call last):
File "/opt/conda/envs/CornerNet_Lite/lib/python3.7/multiprocessing/process.py", line 297, in _bootstrap
self.run()
File "/opt/conda/envs/CornerNet_Lite/lib/python3.7/multiprocessing/process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "train.py", line 59, in prefetch_data
raise e
File "train.py", line 55, in prefetch_data
data, ind = sample_data(system_config, db, ind, data_aug=data_aug)
File "/test/CornerNet-Lite/core/sample/init.py", line 5, in data_sampling_func
return globals()[sys_configs.sampling_function](sys_configs, db, k_ind, data_aug, debug)
File "/test/CornerNet-Lite/core/sample/cornernet_saccade.py", line 169, in cornernet_saccade
border = [0, image.shape[0], 0, image.shape[1]]
AttributeError: 'NoneType' object has no attribute 'shape'

[ybai62868]

Not *.zip but *.jpg. And you also need create a folder named annotations which should contains instance_train/val{}.json for your training and testing in the coco dir.

[cwjhx]

the following is my structure according to the document
+CornerNet-Lite
+data
+coco
+images
+trainval2014
+ *.jpg
+minival2014
+ *.jpg
+testdev2017
+ *.jpg
+annotations
-instances_trainval2014.json
-instances_minival2014.json
-instances_testdev2017.json
but I met the same problem.

[yangkai12]

i met the same issue,how to solve it? thanks

[ybai62868]

The reason why you meet this issue is that your model can't read the image successful. So carefully check the xxx.py in core/dbs. The original repo has no bug with that problem and I also successfully train the CornerNet-Lite on my own dataset. The only drawback is that the training speed is so slow :<

[shengmingkai]

i met the same issue,how to solve it? thanks

do you hava solve it? i met the same issue.my structure is like yours.

[SeeeeShiwei]

do you hava solve it?

[qutrino]

I had the same problem, and found the workaround of it.

• trainval2014 <- jpgs from train2014.zip + val2014.zip
• minival2014 <- jpgs from val2014.zip
• testdev2017 <- jpgs from test2017.zip

[WIll-Xu35]

Hi all, I met the same problem here. I only modified the gpu number and the rest of the codes are not touched.

It seems that the code is combining wrong pairs of directory and image image. For example, combining test directory with val image name, resulting in a wrong image file path.

[ZCDu]

I need help.I also meet this problem. Trying all the suggestions above,I can not get the true. ''NoneType' object has no attribute 'shape'' is being here whatever i do.