CNNArch2Gluon issueshttps://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/issues2022-02-15T11:16:06+01:00https://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/issues/9Generate Network execution based on Training and Test data2022-02-15T11:16:06+01:00Jonas RitzGenerate Network execution based on Training and Test dataSometimes you want to execute your network with some training or test data examples and e.g. visualize how it performs. Therefore there is yet C++ Code generated which enables an execution of the network.
Unfortunately, the loading of th...Sometimes you want to execute your network with some training or test data examples and e.g. visualize how it performs. Therefore there is yet C++ Code generated which enables an execution of the network.
Unfortunately, the loading of the data has to be done by hand, even if you want to execute the network with training data, for example when loading images or importing hdf5 data.
Therefore, the plan is to let the execution be generated (aditionally in python) and let the user of the framework only insert an index of the training or test data point which he wants to be executed, in order to then receive the prediciton and the label and compare in help of his code. In this context the DataLoader can be reused in the execution, but for that it must be available in the execution.https://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/issues/6Upgrade Reinforcement learning code to python 3 / mxnet 1.72021-10-19T15:14:32+02:00Evgeny KusmenkoUpgrade Reinforcement learning code to python 3 / mxnet 1.7@tristan_hoefer probably something you should look into
@mattis.hoppe fyi@tristan_hoefer probably something you should look into
@mattis.hoppe fyiTristan HöferTristan Höferhttps://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/issues/5Save results more often than once per epoch2021-10-19T15:10:05+02:00Evgeny KusmenkoSave results more often than once per epochCurrently, results are only saved once per epoch, which is problematic for large data sets. Consider saving multiple times per epoch.Currently, results are only saved once per epoch, which is problematic for large data sets. Consider saving multiple times per epoch.https://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/issues/4Check if if-else is required2020-11-12T19:20:19+01:00Julian Johannes Steinsberger-DührßenCheck if if-else is requiredhttps://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/blob/master/src/main/resources/templates/gluon/CNNSupervisedTrainer.ftl#L323https://git.rwth-aachen.de/monticore/EmbeddedMontiArc/generators/CNNArch2Gluon/-/blob/master/src/main/resources/templates/gluon/CNNSupervisedTrainer.ftl#L323Evgeny KusmenkoEvgeny Kusmenko