breezelj opened a new issue #18002: resnext model problem URL: https://github.com/apache/incubator-mxnet/issues/18002 ## Description (A clear and concise description of what the bug is.) when I trained faster rcnn with resnext backbone and pretrained model from [http://data.mxnet.io/models/imagenet/resnext/101-layers/resnext-101-0000.params](url), mAP is very low, which is or so 0.001, but resnet is ok, Is there any problem with resnext pretraining model ### Error Message (Paste the complete error message. Please also include stack trace by setting environment variable `DMLC_LOG_STACK_TRACE_DEPTH=10` before running your script.) ## To Reproduce (If you developed your own code, please provide a short script that reproduces the error. For existing examples, please provide link.) ### Steps to reproduce (Paste the commands you ran that produced the error.) 1. 2. ## What have you tried to solve it? 1.I have tried to train without resnext pretrainde model, the mAP is Almost the same like 0.001, it seems the pretrained model doesnot work 2. ## Environment We recommend using our script for collecting the diagnositc information. Run the following command and paste the outputs below: ``` curl --retry 10 -s https://raw.githubusercontent.com/dmlc/gluon-nlp/master/tools/diagnose.py | python # paste outputs here ```
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
