Enable different model configuration specified by the config Json file. Added a pre-trained RNN model (-200 mV, test version) ~3X faster basecalling when using GPU. Enable cloud training using Google Cloud ML Engine. Enable distributed training process, support multiple GPU training.
0.3
New option added --beam <beam_width> Default now using a beam search decoder with a beam width 50, set beam_width to 0 to use the previous greedy decoder. Beam search decoder greatly reduced the deletion rate.
0.2
0.1.4
Add fastq output, and provide the quality score output.