Steven Du

Sorry, I can't tell where I forked this project. However from its name I think it's a 3-gram Englsih language model. Hope someone could help. Ref: https://github.com/micheleasara/Language-Models https://www.analyticsvidhya.com/blog/2019/08/comprehensive-guide-language-model-nlp-python-code/ https://web.stanford.edu/class/cs124/lec/languagemodeling.pdf

Here is my result on the default setting: python driver.py parsed parameters: { "grad_clip": 5, "rnn_relu_encoders": 0, "dataset": "flickr8k", "image_encoding_size": 256, "eval_max_images": -1, "drop_prob_decoder": 0.5, "word_encoding_size": 256, "max_epochs": 50, "eval_batch_size":...

? Any update ?

哪个好呢？　

From its name , I think it is checking whether the input is at least 2d or a [csr](http://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.sparse.csr_matrix.html) matrix .

Cool, @BobLiu20 's fix works.

Any update?

It may caused by sourceforge.net at that time their server is not stable.

I made no change and yet have this problem occasionally. ``` th relatedness/main.lua --model dependency --layers 1 --dim 300 --epochs 10 ```

You don't have the utils folder yet. You need [install](http://kaldi.sourceforge.net/install.html) Kaldi first, then in the ./egs/ folder you can find many utils folders.