If larger corpora are processed, the LDA implementation takes a while to start the sampling. However, the status information can be interpreted in such a way that the program crashed because it seems to be frozen at iteration 0. In reality, however, everything works as it should. One should change this by displaying "Initializing LDA model" or something like that until the current iteration is > 0.
If larger corpora are processed, the LDA implementation takes a while to start the sampling. However, the status information can be interpreted in such a way that the program crashed because it seems to be frozen at iteration 0. In reality, however, everything works as it should. One should change this by displaying "Initializing LDA model" or something like that until the current iteration is > 0.