v0.7.7-p0

• Support for conversion of YOLO models
• Support for models with multiple embedding layers with different input_dims

v0.7.6-p0

Support for AlphaDropout, GaussianDropout SpatialDropout1D, SpatialDropout2D and SpatialDropout3D.

v0.7.5-p0

• Add support for standalone Softmax layer.
• Fix import of standalone ReLU layer without maximum value.

v0.7.4-p0

Support for Permute layer added.

v0.7.3-p0

Fix invalid shape of bias matrix in GRU for reset_after=False

v0.7.2-p0

Calculate hash from model weights and store to JSON

v0.7.1-p0

• Add support for Embedding layers
• Add support for GRU layers
• Fix missing inlines resulting in duplicate function definitions on some compilers

v0.7.0-p0

Adds support for the following layer types:

• Bidirectional
• LSTM
• TimeDistributed

v0.6.0-p0

API-breaking change: Increase dimensionality of tensors from 3 to 5 (needed for future development, like LSTMs and TimeDistributed):

• tensor3 -> tensor5
• shape_hwc -> shape5
• tensor3::get_yxz -> tensor5::get
• tensor3::set_yxz -> tensor5::set

Feature:

• Enable dense layers for non-flattened input tensors.

Fix:

• Safeguard softmax implementation against NaNs.

v0.5.4-p0

• Slight performance improvements