DeepTextSpotter

DeepTextSpotter copied to clipboard

Fine tuning for custom dataset ?

1

Can we fine tuning this model for our custom dataset ? So, it doesn't need to training it from scratch

adifdwimaulana

In model.py ``` def create_models(buckets = [25, 50, 100], phase = caffe.TRAIN): transformers = create_spatial_transformers(buckets, phase) proposal_net = create_yolo(phase) recog = create_recognizer(phase) return proposal_net, transformers, recog ``` Here in this...

Rubseena

demo.py error!

6

Hello, Excuse me, your demo.py can only test videos, can't test pictures？

lfdeep

no module named cmp_trie

9

Hi , thanks for your code ! I have two prolems : 1、I modify the train.py  and add my path of data in the train.py , run python train.py...

19931991

Hi, I want to extract words from image documents together with their coordinates in a key value pair method.Is it possible through this.Please help

Rubseena

cmp_trie undefined symbol error on running demo.py

8

I want to run deeptextspotter in CPU. Is it possible to install and run deeptextspotter on CPU or not?. After installations on running demo.py , I face the issue :...

frozenscrypt

> hi, > the train list is just txt with the image paths. > each image in the should have corresponding txt file, where each line corresponds to word. >...

liuqifan67

Hi,Thank you for sharing this code. I am retraining. RPN only learning. How do you train ocr? dataset 0 0.5150039983297702 0.23366862738313787 0.1304073456352152 0.02778075479762286 -0.012530675040536395 Gachisoft train.txt 3333.jpg 3333.jpg vaild.txt 3333.jpg...

KyungJuJeon

Compile error with ctc_loss_layer

6

I'm getting the errors below when compiling the requisite version of Caffe. Everything else seems fine prior to the ctc_loss_layer. I recently upgraded to Ubuntu 16.04, CUDA 9.0, and NVIDIA...

mattroos

How to pre-train？

3

Hi, I encountered some problems in pre-training. First of all, I want to confirm a few questions. 1) optim2.step(1): in this step, are you training on Regional Proposals or Best...

Sam-Xin