Something wrong about training

[wu-yz]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

[wu-yz]

Is there a trained model？I want to run a demo.

[namtuanly]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

[namtuanly]

Is there a trained model？I want to run a demo.

Yes, we have released the pre-trained models of both FinTabNet and PubtabNet. Please check the pre-trained models and how to run the demo in README.md.

[wu-yz]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

[wu-yz]

Is there a trained model？I want to run a demo.

Yes, we have released the pre-trained models of both FinTabNet and PubtabNet. Please check the pre-trained models and how to run the demo in README.md.

Thank you very much for replying!

[namtuanly]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

Can you show the whole error message, then I will try to check the reason.

[wu-yz]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

Can you show the whole error message, then I will try to check the reason.

After running "data_preprocess_fintabnet.py",I find the several folders were empty.Is there anything wrong with fintabnet datasets?

[namtuanly]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

Can you show the whole error message, then I will try to check the reason.

After running "data_preprocess_fintabnet.py",I find the several folders were empty.Is there anything wrong with fintabnet datasets?

I think you have some problems when preparing the jsonl file of FinTabNet. This jsonl file is the same as the one of PubTabNet. I will publicize the jsonl as well as the table images of FinTabNet and let you know soon.

[wu-yz]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

Can you show the whole error message, then I will try to check the reason.

After running "data_preprocess_fintabnet.py",I find the several folders were empty.Is there anything wrong with fintabnet datasets?

I think you have some problems when preparing the jsonl file of FinTabNet. This jsonl file is the same as the one of PubTabNet. I will publicize the jsonl as well as the table images of FinTabNet and let you know soon.

Thank you so much!

[namtuanly]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

Can you show the whole error message, then I will try to check the reason.

After running "data_preprocess_fintabnet.py",I find the several folders were empty.Is there anything wrong with fintabnet datasets?

I think you have some problems when preparing the jsonl file of FinTabNet. This jsonl file is the same as the one of PubTabNet. I will publicize the jsonl as well as the table images of FinTabNet and let you know soon.

I upload the Python script extract_table_images_FinTabNet.py for extracting table images and making the annotation file (like PubTabNet) from FInTabNet dataset. After that, you can run "data_preprocess_fintabnet.py" to prepare the training dataset for FinTabNet.

[wu-yz]

When running: sh ./table_recognition/expr/table_recognition_dist_train.sh AssertionError: OCRFinTabDataset: TableHardDiskLoader: /datasets/mmocr_fintabnet_recognition_0726_train/StructureLabelAddEmptyBbox_train/ is not exist How can I deal with this problem?

Did you prepare the training data for FinTabNet? You need to run "data_preprocess_fintabnet.py" to prepare the training data for FinTabNet.

Yes,I did.But the mistake still appeared.I'll try it again.

Can you show the whole error message, then I will try to check the reason.

After running "data_preprocess_fintabnet.py",I find the several folders were empty.Is there anything wrong with fintabnet datasets?

I think you have some problems when preparing the jsonl file of FinTabNet. This jsonl file is the same as the one of PubTabNet. I will publicize the jsonl as well as the table images of FinTabNet and let you know soon.

I upload the Python script extract_table_images_FinTabNet.py for extracting table images and making the annotation file (like PubTabNet) from FInTabNet dataset. After that, you can run "data_preprocess_fintabnet.py" to prepare the training dataset for FinTabNet.

OK，I'll give another try.It is appreciated for answering my question in your busy time.

[vkrtsind]

Is there a trained model？I want to run a demo.

Yes, we have released the pre-trained models of both FinTabNet and PubtabNet. Please check the pre-trained models and how to run the demo in README.md.

Thank you very much for replying!

[vkrtsind]

While running on CPU Machine - python demo.py Facing ERROR -

Traceback (most recent call last): File "demo.py", line 6, in from mmdet.apis import init_detector File "/home/n14688/mmdetection/mmdet/apis/init.py", line 2, in from .det_inferencer import DetInferencer File "/home/n14688/mmdetection/mmdet/apis/det_inferencer.py", line 22, in from mmdet.evaluation import INSTANCE_OFFSET File "/home/n14688/mmdetection/mmdet/evaluation/init.py", line 4, in from .metrics import * # noqa: F401,F403 File "/home/n14688/mmdetection/mmdet/evaluation/metrics/init.py", line 5, in from .coco_metric import CocoMetric File "/home/n14688/mmdetection/mmdet/evaluation/metrics/coco_metric.py", line 16, in from mmdet.datasets.api_wrappers import COCO, COCOeval, COCOevalMP File "/home/n14688/mmdetection/mmdet/datasets/init.py", line 31, in from .utils import get_loading_pipeline File "/home/n14688/mmdetection/mmdet/datasets/utils.py", line 5, in from mmdet.datasets.transforms import LoadAnnotations, LoadPanopticAnnotations File "/home/n14688/mmdetection/mmdet/datasets/transforms/init.py", line 6, in from .formatting import (ImageToTensor, PackDetInputs, PackReIDInputs, File "/home/n14688/mmdetection/mmdet/datasets/transforms/formatting.py", line 11, in from mmdet.structures.bbox import BaseBoxes File "/home/n14688/mmdetection/mmdet/structures/bbox/init.py", line 2, in from .base_boxes import BaseBoxes File "/home/n14688/mmdetection/mmdet/structures/bbox/base_boxes.py", line 9, in from mmdet.structures.mask.structures import BitmapMasks, PolygonMasks File "/home/n14688/mmdetection/mmdet/structures/mask/init.py", line 3, in from .structures import (BaseInstanceMasks, BitmapMasks, PolygonMasks, File "/home/n14688/mmdetection/mmdet/structures/mask/structures.py", line 12, in from mmcv.ops.roi_align import roi_align File "/home/n14688/anaconda3/envs/MTL/lib/python3.8/site-packages/mmcv/ops/init.py", line 2, in from .active_rotated_filter import active_rotated_filter File "/home/n14688/anaconda3/envs/MTL/lib/python3.8/site-packages/mmcv/ops/active_rotated_filter.py", line 10, in ext_module = ext_loader.load_ext( File "/home/n14688/anaconda3/envs/MTL/lib/python3.8/site-packages/mmcv/utils/ext_loader.py", line 13, in load_ext ext = importlib.import_module('mmcv.' + name) File "/home/n14688/anaconda3/envs/MTL/lib/python3.8/importlib/init.py", line 127, in import_module return _bootstrap._gcd_import(name[level:], package, level) ImportError: /home/n14688/anaconda3/envs/MTL/lib/python3.8/site-packages/mmcv/_ext.cpython-38-x86_64-linux-gnu.so: undefined symbol: _ZNK2at6Tensor6narrowElll (MTL) n14688@n14688:~/MTL-TabNet/table_r

[vkrtsind]

Can we demo.py on CPU machine ?