returnn
returnn copied to clipboard
rwth-i6
The RWTH extensible training framework for universal recurrent neural networks
The order of axes should never matter. But when a single dim tag can occur multiple times in a tensor (`Data`), it does matter. E.g. for operations like `SoftmaxOverSpatialLayer` on...
Removing the `-std=...` flag as default in #896 caused the breaking of many setups, as the i6 environment is not properly reflected by the automatic test. Before we continue altering...
``` % python3 tests/test_TFEngine.py test_engine_train Installed libSegFault.so. TF version: 1.14.0 2020-06-09 14:03:19.232834: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX...
During fast Baum-Welch training using the FST from Sprint, which currently relies on python2, there is a Pickle protocol incompatibility. This solution proposed by Wei Zhou solves this problem.
Under the Berne Convention, the absence of a license means that no rights granted whatsoever. As the LICENSE stands, downloading the source from this repo (e.g., cloning to the local...
The network is: ``` network = { "output": {"class": "rec", "from": "data", "unit": { "start": {"class": "copy", "from": "prev:output"}, "slices": {"class": "slice_nd", "from": "base:data", "start": "start", "size": None}, # [B,T[B],slice[B,T],D]...
A `Data` object has `time_dim_axis` and `feature_dim_axis`. There are many automatic rules how to automatically define and set them. But these rules are somewhat arbitrary and not always straight-forward. Many...
When the layer is inside a recurrent loop, uses a mask which depends on the previous output and has an input which is not dependent on the output, then there...