Hi! The url (http://u.cs.biu.ac.il/~nlp/wp-content/uploads/lexical_inference.zip) in download_data.sh for BLESS and LEDS seems unavailable now. It returns 403 forbidden when trying to access. I wonder if there is any suggestion on a replacement? Thanks!

Some typos in the code as I see them. Thanks.

#7

#6

Hi,

I am converting the PR into an issue. I am also seeking long-term advice for working with noncommercial licenses for academic purposes.

Thanks, Yifei

Hi @yifeim!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

Some typos in the code as I see them. Thanks.

I'm running this code for the earthquake data and had to do some readjustments as now I'm also including depth in the dataset so spatial locations are now 3d (instead of being 2d: lat and long)

Now I'm facing this issue which is due to backpropagation through the neural ode (odjoint_ode) and I really have no idea what the problem is. Can someone help me with this?

-- Process 0 terminated with the following error: Traceback (most recent call last): File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 59, in _wrap fn(i, *args) File "/home/ne12/Downloads/neural_stpp-main/train_stpp.py", line 145, in main _main(rank, world_size, args, savepath, logger) File "/home/ne12/Downloads/neural_stpp-main/train_stpp.py", line 370, in _main loss.backward() File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/tensor.py", line 245, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/autograd/init.py", line 145, in backward Variable._execution_engine.run_backward( File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/autograd/function.py", line 89, in apply return self._forward_cls.backward(self, *args) # type: ignore File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/adjoint.py", line 126, in backward aug_state = odeint( File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/odeint.py", line 77, in odeint solution = solver.integrate(t) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/solvers.py", line 28, in integrate self._before_integrate(t) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/rk_common.py", line 161, in _before_integrate f0 = self.func(t[0], self.y0) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/misc.py", line 191, in forward return self.base_func(t, y) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/misc.py", line 159, in forward return self.mul * self.base_func(-t, y) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/misc.py", line 138, in forward f = self.base_func(t, _flat_to_shape(y, (), self.shapes)) File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/adjoint.py", line 93, in augmented_dynamics _params = tuple(torch.as_strided(param, (), ()) for param in adjoint_params) # noqa File "/opt2/software/Anaconda3/2020.11/lib/python3.8/site-packages/torchdiffeq/_impl/adjoint.py", line 93, in <genexpr> _params = tuple(torch.as_strided(param, (), ()) for param in adjoint_params) # noqa RuntimeError: setStorage: sizes [], strides [], storage offset 0, and itemsize 4 requiring a storage size of 4 are out of bounds for storage of size 0

https://github.com/facebookresearch/neural_stpp/blob/4258cee81b40e7573bd8289a74c0006d8eace722/models/temporal/basic.py#L37

Hawkes process is giving negative loss because loglik is becoming greater than compensator.

https://github.com/facebookresearch/neural_stpp/blob/4258cee81b40e7573bd8289a74c0006d8eace722/models/temporal/basic.py#L37

Hawkes process is giving negative loss because loglik is becoming greater than compensator.

https://github.com/facebookresearch/neural_stpp/blob/4258cee81b40e7573bd8289a74c0006d8eace722/models/spatial/jumpcnf.py#L29

Is it possible for the authors to include for more comments for this class. I am finding it difficult to understand the logic of your code ?