* Update TVM to latest

* remove darknet from testing due to cffi

x = np.transpose(img, (2, 0, 1))[np.newaxis, :]
TypeError: an integer is required

* add extern lib tutorial

* do fix

* add tutorial for mali gpu

* update submodule version

* fix doc error

* fix server error

* fix server in test

* Explain how to generate module library

* Small fix

* Add compile library tutorial

* Clean output

* Refactor with sphinx gallery

* Refactor

* Change title and other minor fixes

* keras frontend tutorial

* fix

* update

* fix

* use generated onnx model

* fix tests

* fix lint

* remove log filter

* add vgg

* fix tests

* update tests

* fix download

* fix ci

* fix tutorial url

* clean cache

* add coreml

* fix bool

* fix flatten in fullyconnected

* fix duplicate flatten

* fix syntax

* add tutorial

* fix mxnet flatten, fix tutorials

* fix flatten issue

* fix lint

* [TUTORIAL] Deploy the Pretrained Model on Raspberry Pi

* [TUTORIAL] Improve

* [TUTORIAL] Improve

* [TUTORIAL] Improve

* [TUTORIAL] Improve

* update

* back to color

* [TEST] Xavie initialization for benchmarks

* remove additional line

* use resnet v2

* fix

* add onnx

* fix

* [Tutorial] mxnet

update

add from_gluon

add to __init__

fix tutorial and from_gluon

fix doc lint

merge from_mxnet

fix

fix

fix tutorial

fix

fix header

* fix tutorial

* fix data

* fix

* resnet example merged to imagenet

* merge with master

* [TUTORIAL] Move mobilenet to tutorial, fix precompute_prune

* Some language improvements