Yuandong Tian

@hejin @l1t1 what version of pytorch did you use? We use PyTorch 1.0.

@pawni Are you using `experimental` branch? It is under development now. I will fix it in the next few days so that you can run whatever Python environment and use...

The assignment `bk[:] = v.squeeze()` is not dimension-consistent so the `try catch` blocks fall into debug mode. See https://github.com/pytorch/ELF/blob/master/src_py/elf/utils_elf.py#L211 Could you print out the size of `bk` and size of...

When you call  `e.addField("a")` somewhere in the code, make sure `.addExtents` has the correct size. E.g., in your case it should be ``` e.addField("a").addExtents(batchsize, {batchsize}) ``` where `batchsize = 128`....

@downseq remove ``--persistent_tree`` would clean up the existing tree before each move. See here: https://github.com/pytorch/ELF/blob/master/src_cpp/elf/ai/tree_search/mcts.h#L142

@downseq It is always helpful. If the memory allows, this should always help in boosting the performance with zero additional cost. So why not?

@kootsoop Ok, you need to specify the text region (and provide a bbox) for your new image.