Taras Sereda

@keonlee9420 overall great work, thanks for sharing your implementation! Though reference implementation of sdtw has a limitation, that it supports only a batch of sequences of the same length. this...

hey @keonlee9420, current implementation is not touching various lengths sequences inside S-DTW part. being more specific ``` # targets shape - 2 x 200 x 80 target_lenghts=[200, 180] # pred...

Thanks for the suggestion. I've tried with MXNET_ENGINE_TYPE=NaiveEngine MXNet starts as Naive Engine - as stated in logs. still I can't stop on break point specified. How do you check...

Hey, thanks for sharing this implementation! I have few questions. Have you trained SSD300 on VOC data initialized from VGG16 feature extractor in your implementation? The parameters in checkpoint looks...

Hi, thanks for the answer. I have few questions in your code: * variance for encoding bounding boxes: `nets.ssd_common.tf_ssd_bboxes_encode_layer` ``` feat_cy = (feat_cy - yref) / href / prior_scaling[0] feat_cx...

Hey! Thanks for explanation! No annotation label used to avoid false positive on the image regions while training. It's clear. I'm working on training SSD with empty frames, covered with...

I figured how to load the parameters, though with the hack. 1. I obtained model's config by doing this: ``` ckpt_name = "stt_ua_fastconformer_hybrid_large_pc" cfg = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_name=ckpt_name, return_config=True) omegaconf.OmegaConf.save(cfg, f="cfg.yaml") ```...

Hi. I've played a little with your Docker file and created new version. it works fine for me with new caffe distribution. It's based on Ubuntu 14.04. Currently I've created...

setting `"-mmacosx-version-min=10.12"` helps to build `pynini` on macOS Venture 13.5 @david-waterworth thank you for sharing this workaround