Neural Network

Current implementation of Go binding can not specify options.

GPUOptions struct is in internal package. And go generate doesn't work for protobuf directory. So we can't specify GPUOptions for NewSession.

Followup to pytorch/pytorch#74955 (comment).

It turns out that that cmake version was just bad and we can now unpin cmake once again.

cc @seemethere @malfet @pytorch/pytorch-dev-infra

fitDataset() expects a Dataset that produces elements of a certain shape, with matching batch sizes etc., and throws errors (from standardizeDataIteratorOutput()) when the conditions are not met. These errors should be tested.

In gensim/models/fasttext.py:

    model = FastText(
        vector_size=m.dim,
        vector_size=m.dim,
        window=m.ws,
        window=m.ws,
        epochs=m.epoch,
        epochs=m.epoch,
        negative=m.neg,
        negative=m.neg,
        # FIXME: these next 2 lines read in unsupported FB FT modes (loss=3 softmax or loss=4 onevsall,
        # or model=3 supervi

Describe the issue:
During computing Channel Dependencies reshape_break_channel_dependency does following code to ensure that the number of input channels equals the number of output channels:

in_shape = op_node.auxiliary['in_shape']
out_shape = op_node.auxiliary['out_shape']
in_channel = in_shape[1]
out_channel = out_shape[1]
return in_channel != out_channel

This is correct

Check if test_random_gen_accumulative_additive_additive still crashes in pytorch 1.10.1

Originally posted by @edgarriba in kornia/kornia#1611 (comment)

paddle-mobile将开发一个新的版本，为了：

• 支持Paddle Fluid
• 更小的体积
• 更快的速度
• 更广泛地支持各种arm设备和终端平台

因此，paddle-mobile将会进行一次完全的重构，从框架设计到代码开发。在新版本开发完成后，将会删除原有mobile-deep-learning的代码。新版本开发期间，代码将放置在paddle-mobile repo的一个子目录下。对于子目录的命名，目前有3个候选，希望大家投票：

• 👍 zygote
• 👎 paddle
• ❤️ fluid

有更好的建议，请回复issue。相关issue：#121
另外，待新版本代码开发完成，移除老版本mobile-deep-learning代码后，新版本代码将移出子目录，直接放置在paddle-mobile repo下面。