zhiqic / chartreader Goto Github PK
View Code? Open in Web Editor NEW[ICCV 2023] ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules
[ICCV 2023] ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules
我进行了训练detection的部分,在bar chart上得到了很好的结果,但在line chart和bar chart上得到的结果很差,并注意到train部分的代码是“bar only”,请问我讲如何更改得以训练识别line chart和pie chart呢
I have a question about the KPDetection and the KPGrouping. Do they use the same dataset to train? Why is the argument data_dir
different? The training dataset is only one. But there are a lot of errors erupt coming out while I am training the KPGrouping. More then that, the result of the KPDetection is not well.
The top picture is the KPDetection result using the default config from json file KPDetection.json
which is in the config
directory.
Hi. has the repo been moved? Will it be re-posted?
I followed the readme file and trained models for step 1 and 2, but didn't seem to know how to get the Component Position & Type Prediction model or output.
Where is the pretrained model? Is there have some code tell me how to use model to inference on some dataset? Or is there have a huggingFace line to use your model?
Hello,
Could you share with me the model .pkl file? I would like to evaluate it for my research thesis.
Thanks in advance,
Navina
Hey @zhiqic 😀 - I was wondering if you could share a .json file of bounding box test predictions for the public EC400K test set (e.g. in the COCO format: [x,y,width,height]). This way you don't have to share the trained model weights but we would still be able to run our metrics and have your best model as a baseline in our research paper. This would be super helpful and we'd be happy to acknowledge your contribution!
Best, Till
I passed the training data set, it raises index error. The categories_id in dataset and code are not matched. Can you please specify clearer the id numbers? I got index errors and try to fix it according to the training dataset, which doesn't work and made things way more complicated.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 6 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 5 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 6 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 4 is out of bounds for axis 1 with size 3
0%| | 4/50000 [00:00<27:28, 30.34it/s]Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 6 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 5 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 4 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 5 is out of bounds for axis 1 with size 3
0%| | 8/50000 [00:00<26:41, 31.21it/s]Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 4 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 6 is out of bounds for axis 1 with size 3
Shuffling...
Data extraction error occurred.
Traceback (most recent call last):
File "/home/ubuntu/ChartReader/train_extraction.py", line 127, in train
training, ind = sample_data(training_db, ind)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/ubuntu/ChartReader/sampling_function.py", line 528, in sample_data
center_heatmaps[b_ind, category, yce, xce] = 1
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
IndexError: index 4 is out of bounds for axis 1 with size 3
Too many extraction errors. Terminating...
0%|
the trained baseline files' link is unuseful [https://drive.google.com/file/d/1qtCLlzKm8mx7kQOV1criUbqcGnNh58Rr/view?usp=sharing]
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.