Kerolos ghobrial
Kerolos ghobrial
hello everyone, Does anyone know how to save the proper metafile or (.pb format) to load from c++? furthermore, should I initialize a session and feed it into tflearn.DNN function?...
Hello @neumicha , @savovs did you solve that ?
dear @WeiyiLi and @BeautyMess :+1: are you able now to convert the model to tflite? thanks in advance.
hello, @sabrinatuli I have exactly the same problem. did you solve it? what i should change in my config file?
dear @peace195 :+1: how can I get the right format (.pb) from training the Yolo v3 model here, not from the original https://pjreddie.com/darknet/yolo/. thanks in advance.
it there any way to train using Multiple GPUs and increase the bach_size of training? because this method (os.environ["CUDA_VISIBLE_DEVICES"] = "0,1") is only occupied the two GPUs memories without using...
thanks for your reply, i really appreciate that. i did a mistake when i decoded the Librispeech test-clean dataset. the 3 gram.arpa is converted to lower case first and then...
thanks for your reply. 1- The remarkable token is only appeared with underscore in the token list, like that (_unremarkable). when i used WP model to get the sub-word sequence...
Hello @tlikhomanenko , 3- I tried to train (SOTA / TDS CTC ) the librispeech dataset based on Letter lexicon. but after 120 epochs, the loss could not be decreased....
Thanks a lot @abhinavkulkarni for your reply. as you suggest to have a look at emission files, to understand and see what is the output looks like in the specific...