Essam Goda

I have Same error.

Hi, I've tried to train my own model on KITTI Odometry for only 5 epoch, here's the accuracy I get: > Sequence: 9 > Translational error (%): 93.34175477374941 > Rotational...

Hi @Huangying-Zhan, I'm trying to implement DeepVO like this [repo](https://github.com/EduardoTayupanta/VisualOdometry) it converts poses to 6-DOF as shown above for training and also the model output is 6-DOF. the question is...

Hi @Huangying-Zhan, the proposed model is predicted pose at 6-DOF format (translation vector concatenate with euler angles) this for I asked to convert this format to 12DoF to for evaluation....

> We have created a probabilistic mapping, so that each Armenian letter is romanized according to the given probabilities. For example, ծ is replaced by ts in 60% of cases,...

thsnks i created transliteration.json file and train the network but it take very long time more than two hours and not stop yet log file : > Loading Files Building...

@Hrant-Khachatrian when i use this `python -u train.py --hdim 1024 --depth 2 --batch_size 200 --seq_len 30 --language hy-AM &> log.txt` my laptop frozen when it start training in lo file...

@TigranGalstyan okay thanks its work but when test on specific file ` python -u test.py --hdim 512 --depth 1 --model 'languages/hy-AM/models/model.hdim512.depth1.seq_len10.bs50.epoch10.0043668122.loss1.71054670304.npz.npy' --language hy-AM --translit_path 't.txt' ` show ``` Loading Files...

he log after training is last lines ``` skipped 0 computing validation loss... validation loss is 2.94090302211 saving to -> languages/hy-AM/models/model.hdim256.depth2.seq_len30.bs100.epoch10.0363901019.loss2.72517724795.npz ``` when i test with this command ``` python...

> you should first install bun if u dont have it and then run bun i or bun install.. its just like npm bun is installed my OS is ubuntu...