GitLab

* Add utils to calculate model complexity info

* remove _InstanceNorm in unittest

* add docstring and increase unittest coverage

* fix deconv_flops_counter_hook to accept different data shape

* test when model is not a common instance

* put flops_counter.py and weight_init.py into mmcv/cnn/utils folder

* fix import name

* reformat some docstrings

* update the scripts with latest one and remove redundant codes

* directly represent a model without string and eval()

* reformat code

* add hswish and hsigmoid

* fix linting

* fix linting

* delete useless staticmethod in cnn/bricks/hsigmoid.py

* forward(x) ==> forward(seld, x)

* add unittests for hsigmoid and hswish

* use torch.equal instead of numpy.equal

* add non_local module

* rewrite non local module comments

* perfect docstring and adjust init function

* not to init norm layer

* Correct initialize when there is a norm

* set normal method for both embedded_gaussian and dot_product

* fix: tanh has not inplace

* feat: add ConvModule with Tanh

* Support conv layers' own `init_weights` method

* Add related unittest about ConvModule init_weight

* make the comments more specific

* use parrots wrapper for norms

* add unittests for is_norm()

* add a test case

* add building bricks of cnn

* add unit tests

* use registry for building bricks

* minor updates

* add scale layer

* add test for scale

* add doc string
Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>