getMLPlatform()
|
|
getUIMLPlatform()
|
|
can_use_gpu()
|
|
get_cpu_preference()
|
|
get_keras_infos()
|
|
set_compute_device(prefercpu)
|
|
getParams(dodec=keras_dict[dgbkeys.decimkeystr], nbchunk=keras_dict['nbchunk'], epochs=keras_dict['epochs'], batch=keras_dict['batch'], patience=keras_dict['patience'], learnrate=keras_dict['learnrate'], epochdrop=keras_dict['epochdrop'], nntype=keras_dict['type'], prefercpu=keras_dict['prefercpu'], withaugmentation=keras_dict['withaugmentation'], withtensorboard=keras_dict['withtensorboard'])
|
|
adaptive_schedule(initial_lrate=keras_dict['learnrate'], epochs_drop=keras_dict['epochdrop'])
|
|
get_data_format(model)
|
|
hasValidCubeletShape(cubeszs)
|
|
getCubeletShape(model)
|
|
rm_tree(pth)
|
|
getLogDir(examplenm, basedir, clearlogs, args)
|
|
get_model_shape(shape, nrattribs, attribfirst=True)
|
|
getModelDims(model_shape, data_format)
|
|
getModelsByType(learntype, classification, ndim)
|
|
getModelsByInfo(infos)
|
|
getDefaultModel(setup, type=keras_dict['type'], learnrate=keras_dict['learnrate'], data_format='channels_first')
|
|
train(model, training, params=keras_dict, trainfile=None, logdir=None, tempnm=None)
|
|
updateModelShape(infos, model, forinput)
|
|
save(model, outfnm)
|
|
load(modelfnm, fortrain, infos=None, pars=keras_dict)
|
|
transfer(model)
|
|
apply(model, samples, isclassification, withpred, withprobs, withconfidence, doprobabilities, dictinpshape=None, scaler=None, batch_size=None)
|
|
adaptToModel(model, samples, dictinpshape=None, sample_data_format='channels_first')
|
|
adaptFromModel(model, samples, inp_shape, ret_data_format)
|
|
plot(model, outfnm, showshapes=True, withlaynames=False, vertical=True)
|
|
compute_capability_from_device_desc(device_desc)
|
|
getDevicesInfo(gpusonly=True)
|
|
is_gpu_ready()
|
|
need_channels_last()
|
|
get_validation_data(trainseq)
|
|