oyxhust / ssd-text_detection Goto Github PK
View Code? Open in Web Editor NEWA modified SSD model for text detection
A modified SSD model for text detection
the link of vgg16_reduced model is invalid. would you like to give a new one ?
thx.
hello , I have an error while runnig the read_size.py on the synthetic dataset
height, width, channels = cv2.imread(str(gt['imnames'][0, idx][0])).shape AttributeError: 'NoneType' object has no attribute 'shape'
Dear Friend
I want to ask the license of the code if anyone uses for training?
Thank you in advance.
hi,
I am interested in the text detection by SSD ,Could you email me the the trained Model file,
my email is [email protected]
Best wishs
thank you very much
Hi oyxhust,
During training the program, i ran into this problem, do you have any idea about how to deal with it?
Thanks for your time!
issue@thisiscaffe:~/Desktop/text-detection$ python train_synthtext.py
loading data...
finish loading...
INFO:root:Start training with (gpu(0)) from pretrained model /home/issue/Desktop/text-dete ction/model/vgg16_reduced
[15:41:59] src/nnvm/legacy_json_util.cc:190: Loading symbol saved by previous version v0.8 .0. Attempting to upgrade...
[15:41:59] src/nnvm/legacy_json_util.cc:198: Symbol successfully upgraded!
INFO:root:Freezed parameters: [conv1_1_weight,conv1_1_bias,conv1_2_weight,conv1_2_bias,con v2_1_weight,conv2_1_bias,conv2_2_weight,conv2_2_bias]
Traceback (most recent call last):
File "train_synthtext.py", line 76, in
args.lr_refactor_ratio, args.monitor, args.log_file)
File "/home/issue/Desktop/text-detection/train/train_net.py", line 274, in train_net
monitor=monitor)
File "/usr/local/lib/python2.7/dist-packages/mxnet/module/base_module.py", line 460, in fit
for_training=True, force_rebind=force_rebind)
File "/usr/local/lib/python2.7/dist-packages/mxnet/module/module.py", line 429, in bind
state_names=self._state_names)
File "/usr/local/lib/python2.7/dist-packages/mxnet/module/executor_group.py", line 264, in init
self.bind_exec(data_shapes, label_shapes, shared_group)
File "/usr/local/lib/python2.7/dist-packages/mxnet/module/executor_group.py", line 360, in bind_exec
shared_group))
File "/usr/local/lib/python2.7/dist-packages/mxnet/module/executor_group.py", line 638, in _bind_ith_exec
shared_buffer=shared_data_arrays, **input_shapes)
File "/usr/local/lib/python2.7/dist-packages/mxnet/symbol/symbol.py", line 1518, in simp le_bind
raise RuntimeError(error_msg)
RuntimeError: simple_bind error. Arguments:
data: (32, 3L, 300L, 300L)
label: (32, 63L, 5L)
[15:42:01] src/storage/storage.cc:118: Compile with USE_CUDA=1 to enable GPU usage
trying to run " python train_synthtext.py " , it finish loading images and got the error of
anchors = mx.symbol.MultiBoxPrior(from_layer, sizes=size_str, ratios=ratio_str, \ AttributeError: 'module' object has no attribute 'MultiBoxPrior'
Any idea how to fix the error please ?
hi,there
would you like to release your model file ?
thanks.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.