Frank

Installation Problem

1

I installed the hpyerlearn successfully using` python setup.py install `. It shows: ``` #### Welcome to Umbra's HyperLearn! #### #### During installation, code will be compiled down to C /...

Can GPU be used during trainning?

6

Can GPU be used during trainning such as XGBOD ? Thank you !

在训练的过程中, 发现模型并没有使用date信息, 但是在模型初始化的时候, 却对时间数据进行了encoding, 见train函数的代码(来自 exp_ETTH.py ): ``` ..... for i, (batch_x, batch_y, batch_x_mark, batch_y_mark) in enumerate(train_loader): # iter_count += 1 model_optim.zero_grad() pred, pred_scale, mid, mid_scale, true, true_scale = self._process_one_batch_SCINet(...

how can rolling_time_series deal with big data ?

6

I have a 7m rows dataframe to deal with and want to use rolling_time_series in tsfresh. Whether using dask or not, I find it impossible to make it available. Because...

Use SM kernel in Fully Bayesian GPs show errors

8

Follow the Fully Bayesian GPs example, I change the RBF kernel to SpectralMixture Kernel, as follows: ``` class ExactGPModel(gpytorch.models.ExactGP): def __init__(self, train_x, train_y, likelihood): super(ExactGPModel, self).__init__(train_x, train_y, likelihood) self.mean_module =...

Can this algorithm use GPU to accelearte trainning? Thank you !

Can this work for jetson nano?

2

Can this work for jetson nano? Thank you!

How can darts deal the variable length inputs? How can I use masking mechanism to deal with inputs with different time_steps?

When I run the example. I have an RuntimeError: mat1 and mat2 shapes cannot be multiplied (18x1 and 18x256)

1

When I run the command python examples/train_task.py --algo_name=mopo --exp_name=halfcheetah --task HalfCheetah-v3 --task_data_type low --task_train_num 2 It shows : ``` File "examples/train_task.py", line 19, in fire.Fire(run_algo) File "/home/lksgcc/.pyenv/versions/anaconda3-5.0.1/envs/mujoco_py/lib/python3.8/site-packages/fire/core.py", line 141, in...

Thank you for your code. But when I run example1, it runs into an error. When it runs to `dataset = Dataset(nsim=nsim, ninit=0, norm=args.norm, nsteps=args.nsteps, device='cpu', sequences=sequences, name='closedloop')` it shows:...