Comments (23)
i am getting this error while running the train.py code...please tell me the way to clear this error
from east.
What data do you use for training? Is it that ICDAR dataset?
from east.
yes .I am using ICDAR2013+2015 data set.can you please tell me how to clear that error
from east.
Something seems to be wrong with the data_generator
output.
What batch size do you use?
CustomTensorboard
shows three samples every time, which means that the code as it is requires a batch size of at least 3, otherwise it will throw an error at that particular line where it failed for you.
from east.
the batch size i am using is 16
from east.
Could you print out the output of this line? https://github.com/kurapan/EAST/blob/master/train.py#L100
Maybe just the shape of data
variable. Something like print(data.shape)
.
Tell me your keras and tf version too, just in case.
from east.
from east.
I am getting this error..and program did not ends
from east.
I can't see any information related to my code from this screenshot.
Please copypaste the entire message related to the error.
And as I said, print out the shape of data
variable that is declared on line 100.
Have you made any changes to the code? I don't remember seeing this kind of output with the filenames.
from east.
(base) F:\New folder\EAST-master>python train.py
Using TensorFlow backend.
Traceback (most recent call last):
File "train.py", line 249, in
main()
File "train.py", line 213, in main
val_data = data_processor.load_data(FLAGS)
File "F:\New folder\EAST-master\data_processor.py", line 864, in load_data
loaded_data = pool.map_async(load_data_process, zip(image_files, itertools.repeat(FLAGS), itertools.repeat(is_train))).get(9999999)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\multiprocessing\pool.py", line 651, in get
self.wait(timeout)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\multiprocessing\pool.py", line 648, in wait
self._event.wait(timeout)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\threading.py", line 552, in wait
signaled = self._cond.wait(timeout)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\threading.py", line 300, in wait
gotit = waiter.acquire(True, timeout)
OverflowError: timeout value is too large
from east.
when I run the code without any changes(as it is)with my dataset directory, I am getting this error.please tell me the reason for this error
from east.
Ah, the timeout value overflow error is some Windows issue. I haven't tested it in Windows as I don't have access to any Windows machine that could be used for machine learning.
Try a number lower than that 9999999
.
You were able to resolve this with some changes?
from east.
(base) F:\New folder\EAST-master>python train.py
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
Using TensorFlow backend.
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_201.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_207.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_204.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_210.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_202.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_208.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_205.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_211.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_203.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_209.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_206.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_212.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_213.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_219.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_202.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_216.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_203.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_214.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_220.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_217.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_204.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_201.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_215.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_205.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_218.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_208.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_211.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_206.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_214.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_209.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_212.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_207.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_215.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_210.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_213.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_217.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_216.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_220.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_218.txt does not exists
text file gt_F:\EAST\Dataset\MLT_val_data_latin\val_data_latin\img_219.txt does not exists
Number of validation images : 0
Training with 1 GPU
WARNING:tensorflow:From C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
2019-02-26 11:35:33.744607: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras_applications\resnet50.py:265: UserWarning: The output shape of ResNet50(include_top=False)
has been changed since Keras 2.2.0.
warnings.warn('The output shape of ResNet50(include_top=False)
'
from east.
when i reduced the number ..the program run..but it doesn't consider the image file..I run the train.py with only 20 validation images and 20 data set images. just for checking...will this be a problem.?
from east.
It says there are no validation images and that the txt files don't exist. Is the path correct?
from east.
yes,the path is correct
from east.
Are there really files img_XXX.txt
in the val_data_latin
directory?
from east.
yes sir,the img_xxx.jpg and gt_img_xxx.txt are in same directory
from east.
but the image.jpg files are read as image.txt files..
from east.
I see one problem now. Windows uses backslash instead of slash. Change it in the get_text_file
function.
Use txt_file.split('\')[-1]
instead of txt_file.split('/')[-1]
.
from east.
img_ (13).txt
main()
File "train.py", line 248, in main
, callbacks=callbacks, verbose=1)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
################################# F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (20).jpg
F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (20).txt
-----------
img_ (20).txt
return func(*args, **kwargs)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras\engine\training.py", line 1418, in fit_generator
initial_epoch=initial_epoch)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 217, in fit_generator
class_weight=class_weight)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras\engine\training.py", line 1217, in train_on_batch
outputs = self.train_function(ins)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in __call__
################################# F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (17).jpg
F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (17).txt
-----------
img_ (17).txt
################################# F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (10).jpg
F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (10).txt
-----------
img_ (10).txt
return self._call(inputs)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1439, in __call__
run_metadata_ptr)
File "C:\Users\VINOTH KUMAR S\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in __exit__
################################# F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (14).jpg
F:\EAST\Dataset\ICDAR2013+2015\ICDAR2013+2015\train_data\img_ (14).txt
-----------
img_ (14).txt
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [16,64,64,1] vs. [16,128,128,1]
[[{{node loss/pred_score_map_loss/mul_4}}]]
from east.
i am getting this error when the train.py program is executed
from east.
Could you tell me what changes you have made to the code?
I don't know how to reproduce your error so you have to tell me more.
from east.
Related Issues (20)
- Interpretation of output?
- The history object HOT 1
- CustomTensorboard and ValidationEvaluator callbacks HOT 1
- Error for input_size other that 512 HOT 1
- No such layer: activation_49 HOT 2
- Access denied HOT 1
- StopIteration error when training HOT 1
- AttributeError: 'LearningRateScheduler' object has no attribute '_implements_train_batch_hooks'
- error in adamw learning rate HOT 2
- The system cannot find the file specified HOT 1
- File "/home/u00012/code/Text-Detection/EAST-keras/model.py", line 13, in resize_bilinear HOT 1
- Run prediction on gpu
- Error in training ICDAR data on CPU
- PAINFULLY slow to do prediction with kurapan/EAST implementation
- Annotations for EAST [help wated]
- Trained Model HOT 1
- model.json Issue
- Unable to run eval.py via the provided json pre-trained model.
- can we custom train for specific number detection like credit card number
- No changes of hmean, precision and recall
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from east.