+1 Built 1.8.0.rc3 from source using instructions [1] on Ubuntu 18.04, AWS EC2 C5.18x CPU instance. Loaded a pre-trained ResNet50 image classification and FasterRCNN object detection inference with pre-trained model [2] [3] and it works as expected.
[1] https://mxnet.apache.org/get_started/build_from_source [2] https://cv.gluon.ai/model_zoo/classification.html#how-to-use-pretrained-models [3] https://cv.gluon.ai/build/examples_detection/demo_faster_rcnn.html Best, Sandeep On Wed, Jan 20, 2021 at 4:06 PM Wei Chu <[email protected]> wrote: > +1 > Built mxnet 1.8.0.rc3 from source with CUDA11.0 on EC2 p4d instance. > Ran mnist training test with both CPU/GPU. > > Best, > Wei Chu > > On 2021/01/19 23:10:21, "Skalicky, Sam" <[email protected]> > wrote: > > Dear MXNet community, > > > > This is the vote to release Apache MXNet (incubating) version 1.8.0. > Voting will start January 19, 17:00:00 PT and close on January 21, 17:00:00 > PT. > > > > Link to release notes: > > https://cwiki.apache.org/confluence/display/MXNET/1.8.0+Release+Notes > > > > Link to release candidate: > > https://github.com/apache/incubator-mxnet/releases/tag/1.8.0.rc3 > > > > Link to source and signatures on apache dist server: > > https://dist.apache.org/repos/dist/dev/incubator/mxnet/1.8.0.rc3 > > > > Please remember to TEST first before voting accordingly: > > +1 = approve > > +0 = no opinion > > -1 = disapprove (provide reason) > > > > Here are the changes comparing to 1.8.0.rc2: > > > > * Extensions bugfixes > > * Updated LICENSE & rat checker > > * fix for R builds > > * Upgrade to oneDNN v1.7 with required bugfixes > > * Fix for testing with CUDA 11, remove cleanup on side threads > > * Fix for building CUDA 11 with Windows > > * Remove temporary fix for RNN in MKLDNN > > > > Best regards, > > Sam Skalicky > > > > > > > > > -- Sandeep Krishnamurthy
