see

see copied to clipboard

Unable to train SVHN Dataset

25

Hello @Bartzi, I'm tring to train SVHN dataset using following train.csv which path is defined in curricum.json as follows  Command for trainning svhn dataset is sudo python3 chainer/train_svhn.py "/root/see-master/datasets/train_dataextract_train/curriculum.json"...

harshalcse

Unable able to Train (SVHN and FSNS)

5

Hi Bartzi, I want to run the **train_svhn.py**, I have prepared the data set as per the instruction given in **Read me** file for running **train_svhn.py**. As per #20 ,...

Devadattaprasad

Prepared Datasets for download

46

I am unable to find the prepared datasets on the site that you have [linked](https://bartzi.de/research/see#) to. Do I need to prepare the datasets myself? Is it possible to get them...

rohit12

FSNS curriculum learning gt files

17

Hi, I have a question about the ground truth files for FSNS curriculum learning. I've created the ground truth file with images containing up to 2 words using this command:...

janzd

saved model

10

Thanks for sharing your code with us. Could you also share your saved model?

un-lock-me

Is there any pre-trained model that can recoginize both alphabets and numbers if they appear in localized image?

33

arsalan993

fsns-demo doesn't work well

4

@Bartzi Hi, I ran the fsns_demo.py using my pictures，but it doesn't work well.The result identified the wrong word and the incorrect bboxs. The process I made my pictures as follows:...

chunhui999

fsns problem

9

Hi,fsns has 4 views img,so how to deal 4 imgs by one network?

wushilian

Problem in evaluation after training the model

19

Hi, I have trained the model on SVHN dataset. I have trained the model on google colab notebook. After training the model the following directory created. **NOTE:** _I have trained...

saq1410

Failed on load weights + Zero Accuracy problems

37

Hi @Bartzi I already successfully train my custom data set (loss score below 0.01) with this command until last epoch: ``` python train_text_recognition.py mytrain/curriculum.json log \ --blank-label 0 \ --batch-size...

rezha130