autograd

🚀 The feature, motivation and pitch

Usage of these two variables in tests is outdated. One should just write in the dtypes in question or use one of the ATen macro dispatch list functions (like get_all_fp_dtypes()).

Alternatives

No response

Additional context

No response

环境

1.系统环境：

• Ubuntu 20.04.2 LTS x86_64
• GLIBCXX: 3.4.28 (libstdc++.so.6.0.28)
• GPU:
  

2.MegEngine版本：1.6.0rc1
3.python版本：Python 3.8.10

The program stuck at net.load when I was trying to use the MegFlow. I wait for more than 10min and there is no sign of finishing it.

Love the book! Ran into this display issue when viewing it on Chrome's PDF viewer:

Description

Implement a YOLO model and add it to the DJL model zoo

References

• https://arxiv.org/abs/1506.02640

Issue to track tutorial requests:

• Deep Learning with PyTorch: A 60 Minute Blitz - #69
• Sentence Classification - #79

Feature details

Due to the similarity, it is easy to confuse qml.X and qml.PauliX, especially since other methods of specifying circuits, e.g., QASM, use x for PauliX. But if a user uses qml.X in their circuit on a qubit device, nothing happens to inform them that the incorrect operation is being used:

@qml.qnode(dev)
def circ():
    qml.PauliX(wires=0)
    qml.Hada

Add a function and module that permits spike-time decoding, as suggested by @schmitts https://twitter.com/sbstnschmtthd/status/1432343373072019461

I think it would be very useful to have learning rate schedulers

• lr_cyclic() (https://arxiv.org/abs/1506.01186, Python source at https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#CyclicLR), and
• lr_cosine_annealing_warm_restarts() (https://arxiv.org/abs/1608.03983, Python source at https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#CosineAnnealin

The init module has been deprecated, and the recommend approach for generating initial weights is to use the Template.shape method:

>>> from pennylane.templates import StronglyEntanglingLayers
>>> qml.init.strong_ent_layers_normal(n_layers=3, n_wires=2) # deprecated
>>> np.random.random(StronglyEntanglingLayers.shape(n_layers=3, n_wires=2))  # new approach

We should upd

Okay, so this might not exactly be a "good first issue" - it is a little more advanced, but is still very much accessible to newcomers.

Similar to the mygrad.nnet.max_pool function, I would like there to be a mean-pooling layer. That is, a convolution-style windows is strided over the input, an