Release note 1.3.0
March 17 2023
All release notes are available at this page .
| Release Notes V1.3.0 |
Date of releaseΒ 17 march 2023 |
Features
Layers
| Native LabVIEW | GPU (CUDA) | |
| Add2D | done | done |
| Add3D | done | done |
| Add4D | done | done |
| Additive Attention | done | done |
| AlphaDropout2D | done | done |
| AlphaDropout3D | done | done |
| AlphaDropout4D | done | done |
| AlphaDropout5D | done | done |
| Attention | done | done |
| Average2D | done | done |
| Average3D | done | done |
| Average4D | done | done |
| AvgPool1D | done | done |
| AvgPool2D | done | done |
| AvgPool3D | done | done |
| BatchNormalization2D | done | done |
| BatchNormalization3D | done | done |
| BatchNormalization4D | done | done |
| BatchNormalization5D | done | done |
| BatchNormalization6D | done | done |
| Bidirectional | done | done |
| Concatenate | done | done |
| Conv1D | done | done |
| Conv1DTranspose | done | done |
| Conv2D | done | done |
| Conv2DTranspose | done | done |
| Conv3D | done | done |
| Conv3DTranspose | done | done |
| ConvLSTM1D | done | Next release |
| ConvLSTM2D | done | Next release |
| ConvLSTM3D | done | Next release |
| Cropping1D | done | done |
| Cropping2D | done | done |
| Cropping3D | done | done |
| Dense | done | done |
| DepthwiseConv2D | done | Next release |
| Dropout2D | done | done |
| Dropout3D | done | done |
| Dropout4D | done | done |
| Dropout5D | done | done |
| Embedding | done | done |
| Flatten | done | done |
| GaussianDropout2D | done | done |
| GaussianDropout3D | done | done |
| GaussianDropout4D | done | done |
| GaussianDropout5D | done | done |
| GaussianNoise2D | done | done |
| GaussianNoise3D | done | done |
| GaussianNoise4D | done | done |
| GaussianNoise5D | done | done |
| GlobalAvgPool1D | done | done |
| GlobalAvgPool2D | done | done |
| GlobalAvgPool3D | done | done |
| GlobalMaxPool1D | done | done |
| GlobalMaxPool2D | done | done |
| GlobalMaxPool3D | done | done |
| GRU | done | done |
| LayerNormalization2D | done | done |
| LayerNormalization3D | done | done |
| LayerNormalization4D | done | done |
| LayerNormalization5D | done | done |
| LSTM | done | done |
| MaxPool1D | done | done |
| MaxPool2D | done | done |
| MaxPool3D | done | done |
| MultiHeadAttention | done | done |
| Multiply2D | done | done |
| Multiply3D | done | done |
| Permute3D | done | Next release |
| Reshape | done | done |
| RNN | done | done |
| SeparableConv1D | done | Next release |
| SeparableConv2D | done | Next release |
| SimpleRNN | done | done |
| SpatialDropout1D | done | done |
| SpatialDropout2D | done | done |
| SpatialDropout3D | done | done |
| Substract2D | done | done |
| Substract3D | done | done |
| Substract4D | done | done |
| Substract5D | done | done |
| TimeDistributed | done | Next release |
| UpSampling1D | done | done |
| UpSampling2D | done | done |
| UpSampling3D | done | done |
| ZeroPadding1D | done | done |
| ZeroPadding2D | done | done |
| ZeroPadding3D | done | done |
Enhancement
βΒ Load H5 model from Keras is now totaly working with HAIBAL.
β We adopt the H5 for saving model.
β Get & Set layer activation now is available.
β Improve Get & Set Idx system security to avoid errors.
β Release U-Net: Convolutional Networks for Biomedical Image Segmentation model
β Added dilation rate for convolution
– AddedΒ 2 β 3 – 4 – 5 -6 D MetricsΒ (AUC, Accuracy, BinaryAccuracy, BinaryCrossentropy, BinaryIoU, CategoricalAccuracy, CategoricalCrossentropy, CategoricalHinge, CosineSimilarity, FalseNegatives, FalsePositives, Hinge, Huber, IoU, KLDivergence, LogCoshError, Mean, MeanAbsoluteError, MeanAbsolutePercentageError, MeanIoU, MeanRelativeError, MeanSquaredError, MeanSquaredLogarithmicError, MeanTensor, OneHotIoU, OneHotMeanIoU, Poisson, Precision, PrecisionAtRecall, Recall, RecallAtPrecision, RootMeanSquaredError, Sensitivity, SensitivityAtSpecificity, SparseCategoricalAccuracy, SparseCategoricalCrossentropy, SparseTopKCategoricalAccuracy, Specificity, SpecificityAtSensitivity, SquaredHinge, Sum, TopKCategoricalAccuracy, TrueNegatives, TruePositives)
LabVIEW compatibility versions
LabVIEW64 2022 are supported with this release. (for LabVIEW 2020 & 2021 release please contact us)
Version of CUDA API
CUDA 11.7 & Β Cudnn 8.5.0
Use our platform installer tool available in download section to make HAIBAL working properly with Cuda (do not install cuda by yourselve our tool is here to simplify your life).
Roadmap
Discover the chronology of the project and the targeted future evolutions.