Time grad (#28)

* initial uncond image gaussian diff

TODO make it work for multivariate vector
add conditioning

* remove tqdm

* initial unet

TODO convert to 1d conv

* initial time grad estimator

* initial training

* initial sampling

* added huber loss

* use SinusoidalPosEmb from wavegrad

* use time diff network

* fix reshaping

* fix missing property

* clip false

* updated api

* added padding

* added circular padding

* use linear schedule

* added more schedules

* added back cosine schedule

* Delete Solar-time-grad.ipynb

* updated estimator API

* not tuple

* renamed to EpsilonTheta

* removed

* added example notebook

* removed some output

* fix requirements

* formatting

* added more options to time-grad

* added article

setup.py

@@ -18,11 +18,10 @@ setup(
         "torch>=1.7.0",
         "gluonts",
         "holidays",
-        "numpy",
-        "pandas>=1.1",
+        "numpy~=1.16",
+        "pandas~=1.1",
         "scipy",
         "tqdm",
-        "pydantic",
         "matplotlib",
         "tensorboard",
         "wandb",