Hi, Great work.! I am more interested on text extraction. Could you guide me which module is being used from the text extraction in the pipeline.

Hi guys, past month Luminoth was archived. You have plans to migrate to another toolkit? The project is awesome.

While running the tabulo --help , I am encountering the following error.
There seem to be a conflict between the two libraries, where each library want some specific version of click. I have downloaded both versions of click, i.e. 6.7 and 7.1.2. but still encountering error.

Traceback (most recent call last):
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 583, in _build_master
    ws.require(__requires__)
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 900, in require
    needed = self.resolve(parse_requirements(requirements))
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 791, in resolve
    raise VersionConflict(dist, req).with_context(dependent_req)
pkg_resources.ContextualVersionConflict: (click 6.7 (/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages), Requirement.parse('click>=7.1.2'), {'Flask'})

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/gurjot/Tabulo/tabenv/bin/tabulo", line 6, in <module>
    from pkg_resources import load_entry_point
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 3252, in <module>
    def _initialize_master_working_set():
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 3235, in _call_aside
    f(*args, **kwargs)
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 3264, in _initialize_master_working_set
    working_set = WorkingSet._build_master()
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 585, in _build_master
    return cls._build_from_requirements(__requires__)
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 598, in _build_from_requirements
    dists = ws.resolve(reqs, Environment())
  File "/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages/pkg_resources/__init__.py", line 791, in resolve
    raise VersionConflict(dist, req).with_context(dependent_req)
pkg_resources.ContextualVersionConflict: (click 6.7 (/home/gurjot/Tabulo/tabenv/lib/python3.8/site-packages), Requirement.parse('click>=7.1.2'), {'Flask'})

Is it normal that the command tabulo predict takes so much time to process (like 30 seconds by image)?

Hi ,

I have few questions on tabulo

1. i am unable to download the checkpoint which is trained on tables i am able to see a cooc dataset faster rcnn and ssd.

2. how does tabulo work? i mean i dont see any installation of tesseract how is the able to display the characters from a table image?

Regards
Sekar

can you please send me the config file that you have used to create the checkpoint 6aac7a1e8a8e ?

Great work. May I ask what training data you used for the pre-trained table detection model? Thanks!

I have tried tabulo predict on one of the pdf images from your sample's but it didn't generate anything, Below is the full message of the output.

Found 1 files to predict.
Neither checkpoint not config specified, assuming accurate.
Checkpoint not present locally. Want to download it? [y/N]: y
Downloading checkpoint...
Importing checkpoint... done.
Checkpoint imported successfully.
2020-02-19 17:16:24.245652: I tensorflow/core/platform/cpu_feature_guard.cc:145] This TensorFlow binary is optimized with Intel(R) MKL-DNN to use the following CPU instructions in performance critical operations: AVX AVX2
To enable them in non-MKL-DNN operations, rebuild TensorFlow with the appropriate compiler flags.
2020-02-19 17:16:24.248831: I tensorflow/core/common_runtime/process_util.cc:115] Creating new thread pool with default inter op setting: 8. Tune using inter_op_parallelism_threads for best performance.
Predicting page_8-min.jpg...OMP: Info #212: KMP_AFFINITY: decoding x2APIC ids.
OMP: Info #210: KMP_AFFINITY: Affinity capable, using global cpuid leaf 11 info
OMP: Info #154: KMP_AFFINITY: Initial OS proc set respected: 0-7
OMP: Info #156: KMP_AFFINITY: 8 available OS procs
OMP: Info #157: KMP_AFFINITY: Uniform topology
OMP: Info #179: KMP_AFFINITY: 1 packages x 4 cores/pkg x 2 threads/core (4 total cores)
OMP: Info #214: KMP_AFFINITY: OS proc to physical thread map:
OMP: Info #171: KMP_AFFINITY: OS proc 0 maps to package 0 core 0 thread 0
OMP: Info #171: KMP_AFFINITY: OS proc 1 maps to package 0 core 0 thread 1
OMP: Info #171: KMP_AFFINITY: OS proc 2 maps to package 0 core 1 thread 0
OMP: Info #171: KMP_AFFINITY: OS proc 3 maps to package 0 core 1 thread 1
OMP: Info #171: KMP_AFFINITY: OS proc 4 maps to package 0 core 2 thread 0
OMP: Info #171: KMP_AFFINITY: OS proc 5 maps to package 0 core 2 thread 1
OMP: Info #171: KMP_AFFINITY: OS proc 6 maps to package 0 core 3 thread 0
OMP: Info #171: KMP_AFFINITY: OS proc 7 maps to package 0 core 3 thread 1
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 13264 thread 0 bound to OS proc set 0
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 12156 thread 1 bound to OS proc set 2
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 16980 thread 2 bound to OS proc set 4
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 17288 thread 3 bound to OS proc set 6
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 22584 thread 4 bound to OS proc set 1
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 18916 thread 5 bound to OS proc set 3
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 22892 thread 6 bound to OS proc set 5
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 896 thread 8 bound to OS proc set 0
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 10468 thread 7 bound to OS proc set 7
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 11156 thread 9 bound to OS proc set 2
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 20656 thread 10 bound to OS proc set 4
OMP: Info #250: KMP_AFFINITY: pid 11852 tid 14932 thread 11 bound to OS proc set 6
done.
{"file": "page_8-min.jpg", "objects": []}

Hello, I found a performance issue in the definition of _build, luminoth/models/ssd/proposal.py, tf.shape(all_anchors)[0] will be calculated repeatedly during program execution, resulting in reduced efficiency. I think it should be created before the loop.

The same issue exists in tf.cast(total_anchors, tf.float32).

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.

I followed the installation process until the following command :

tabulo checkpoint list

I get the following error after executing the command:

Error:
AttributeError: module 'tensorflow' has no attribute 'contrib'

I am guessing its because I am using Tensorflow 2.0 and models dont support it. Is there a quick work around to this ?

I placed the 6aac7a1e8a8e checkpoint dir under Tabulo/luminoth/utils/pretrained_models

and ran from Tabulo:
tabulo server web --checkpoint 6aac7a1e8a8e

and it returned:
Checkpoint not found. Check remote repository? [y/N]: y

Retrieving remote index... done.
No changes in remote index.
Checkpoint isn't available in remote repository either.
Traceback (most recent call last):
File "C:\Users\jay\Anaconda2\envs\py36\Scripts\tabulo-script.py", line 11, in
load_entry_point('tabulo', 'console_scripts', 'tabulo')()
File "c:\users\jay\anaconda2\envs\py36\lib\site-packages\click\core.py", line 722, in call
return self.main(*args, **kwargs)
File "c:\users\jay\anaconda2\envs\py36\lib\site-packages\click\core.py", line 697, in main
rv = self.invoke(ctx)
File "c:\users\jay\anaconda2\envs\py36\lib\site-packages\click\core.py", line 1066, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "c:\users\jay\anaconda2\envs\py36\lib\site-packages\click\core.py", line 1066, in invoke
return process_result(sub_ctx.command.invoke(sub_ctx))
File "c:\users\jay\anaconda2\envs\py36\lib\site-packages\click\core.py", line 895, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "c:\users\jay\anaconda2\envs\py36\lib\site-packages\click\core.py", line 535, in invoke
return callback(*args, **kwargs)
File "c:\users\jay\documents\ml_projects\luminoth\luminoth\tools\server\web.py", line 83, in web
config = get_checkpoint_config(checkpoint)
File "c:\users\jay\documents\ml_projects\luminoth\luminoth\tools\checkpoint_init.py", line 193, in get_checkpoint_config
raise ValueError('Checkpoint not found.')
ValueError: Checkpoint not found.

Additionally, functionality to list existing checkpoints does not work.

I'm running on Windows 10, just cloned the repo this AM.

I'm a complete newbie when it comes to data science, but this project would greatly help mine own, but sadly I cannot run it due to the TF versions and as far as I'm aware Apple doesn't support TF1.5. (I'm using an M1 Mac) Any help is greatly appreciated

When installing Tabulo, I get below:

Installing collected packages: tabulo
  Attempting uninstall: tabulo
    Found existing installation: tabulo 0.2.4.dev0
    Uninstalling tabulo-0.2.4.dev0:
      Successfully uninstalled tabulo-0.2.4.dev0
  Running setup.py develop for tabulo
Successfully installed tabulo

After this, when running below from my CLI:

tabulo --help

I get below error:

-bash: tabulo: command not found

I am running Python on Mac OS X. What am I doing wrong?

i installed tabulo and when I tried to run tabulo --help , I get an error saying Failed to create process. Can someone help me solve it??

After I installed tabulo and run git....,cd tabulo and pip install -e . I tried to run tabulo --help , I get an error saying failed to create process. Anyone knows what's going on?

Error: No such command "sever". when I try to run the Tabulo service using tabulo sever web --checkpoint 6aac7a1e8a8e after downloading and unzipping the pretrained models into the luminoth/utils/pretrained_models directory.

Thanks for your project.

An official docker image would be great to get started quickly.

Hi, please, tell me how can I change the recognition language to Russian?

Predict function doesn't work in command line but well in the web app interface

You should replace :

Open and read the image to predict.

with tf.gfile.Open(path, 'rb') as f:
    try:
        image = Image.open(f).convert('RGB')
    except (tf.errors.OutOfRangeError, OSError) as e:
        click.echo()
        click.echo('Error while processing {}: {}'.format(path, e))
        return

by :

Open and read the image to predict.

with tf.gfile.Open(path, 'rb') as f:
    try:
        image = Image.open(f).convert('RGB')
        img = np.asarray(image)
        img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
        b = cv2.distanceTransform(img, distanceType=cv2.DIST_L2, maskSize=5)
        g = cv2.distanceTransform(img, distanceType=cv2.DIST_L1, maskSize=5)
        r = cv2.distanceTransform(img, distanceType=cv2.DIST_C, maskSize=5)

        # merge the transformed channels back to an image
        transformed_image = cv2.merge((b, g, r))
    except (tf.errors.OutOfRangeError, OSError) as e:
        click.echo()
        click.echo('Error while processing {}: {}'.format(path, e))
        return

to be able to use tabulo predict in command line

Hi I have installed the project and predict api is working but their is no documentation how i can call extract api can you help me with this,

Thanks in advance,

I've downloaded a JPEG into the Tabulo directory (that I've cloned) and tried to run PostMan by importing the curl command onto PostMan
Key as 'image'
Value as '2_resized.jpg'

The error is
{
"error": "Missing image"
}

400 BAD REQUEST Error

Upon hitting the command "tabulo checkpoint list" I got the below response

I haven't got this checkpoint in the list' 6aac7a1e8a8e' though It is present in the luminoth/checkpoints folder.
I have tried hitting the command with another checkpoint it showed in the list -> server web --checkpoint aad6912e94d9
but it says Checkpoint not present locally and downloading... which is never downloaded.

Please help me with this.

#luminoth #checkpoints #tabulo

Thanks.

Hi, I'm trying to use the pre-trained model. I've downloaded the google drive folder and placed it in pretrained_models. When I run tabulo checkpoint list I do not see the local checkpoint.

Any idea what is going on?

Hi,
I have installed all the packages properly and I have been trying the following curl command from my MacBook terminal:

curl -X POST http://localhost:5000/api/fasterrcnn/predict/ -H 'Content-Type: application/x-www-form-urlencoded' -H 'Postman-Token: 70478bd2-e1e8-442f-b0bf-ea5ecf7bf4d8' -H 'cache-control: no-cache' -H 'content-type: multipart/form-data; boundary=----WebKitFormBoundary7MA4YWxkTrZu0gW' -F "image=@/Users/rudra/Desktop/page_12.jpg"
But it keeps outputting an error saying: {"error":"Missing image"}

Can anyone please help me solve this? I also tried -F image=@/Users/rudra/Desktop/page_12.jpg but no success. I even tried converting the curl request into a python post type request, but the same error.

Thanks in advance.

Hi, Great work.! I am more interested on text extraction. Could you guide me which module is being used from the text extraction in the pipeline.