-
icdar.py当中看到了两个txt文件,在py-faster rcnn当中会在ImageSets/Main生成trainval.txt,这个trainval.txt对应图片当中的哪个文件呢?merge_train.txt里面的内容是什么呢?
![default](https://user-images.githubusercontent.com/15090557/38775157-ea76…
-
We ran your codes on ICDAR-13 dataset but not getting results anywhere near to you! Can you please suggest something to get more accurate result??
-
I'm getting the following error:
File "/home/mukut/gitlab/corner/data/icdar.py", line 49, in __init__
ic13_samples = open(ic13_list_path, 'r').readlines()
IOError: [Errno 2] No such file or…
-
Would there be an issue if I change the python code from 2.7 to 3.6 using Automated 2-3 translation?
Also, I wish to train the model on coco dataset, I have prepared the data in ICDAR 2015 format, w…
-
-
@MhLiao Thanks for your work!
-
many thanks to your job
I try to use your new code for the training, but I got some other error like
***********************************************************************************************…
-
![workspace 1_003](https://user-images.githubusercontent.com/16499363/45757009-00136500-bc40-11e8-8f3c-33f08e089c65.png)
while training I am getting this error . please can someone tell me how to p…
-
Hi, did you train sotd on icdar dataset? I have trained it on icdar2015 but the predicted map is all background class. Should I use another loss function such as cross entropy? Thank you!
-
GS e2e Demo
test uses batched real inputs and produces batched outputs
this test is looped (takes several batches of inputs, produces several batches of outputs)
test evaluates results of TT …