rt-light{color:#818182;background-color:#fefefe;border-color:#fdfdfe}.alert-light hr{border-top-color:#ececf6}.alert-light .alert-link{color:#686868}.alert-dark{color:#1b1e21;background-color:#d6d8d9;border-color:#c6c8ca}.alert-dark hr{border-top-color:#b9bbbe}.alert-dark .alert-link{color:#040505}@-webkit-keyframes progress-bar-stripes{from{background-position:1rem 0}to{background-position:0 0}}@keyframes progress-bar-stripes{from{background-position:1rem 0}to{background-position:0 0}}.progress...

 > th,\n.table-active > td {\n  background-color: rgba(0, 0, 0, 0.075);\n}\n\n.table-hover .table-active:hover {\n  background-color: rgba(0, 0, 0, 0.075);\n}\n\n.table-hover .table-active:hover > td,\n.table-hover .table-active:hover > th {\n  background-color: rgba(0, 0, 0, 0.075);\n}\n\n.table .thead-dark th {\n  color: #fff;\n  background-color: #343a40;\n  border-color: #454d55;\n}\n\n.table .thead-light th {\n  color: #495057;\n  background-color: #e9ecef;\n  border-color: #dee2e6;\n}\n\n.table-dark...

 > th,\n.table-active > td {\n  background-color: rgba(0, 0, 0, 0.075);\n}\n\n.table-hover .table-active:hover {\n  background-color: rgba(0, 0, 0, 0.075);\n}\n\n.table-hover .table-active:hover > td,\n.table-hover .table-active:hover > th {\n  background-color: rgba(0, 0, 0, 0.075);\n}\n\n.table .thead-dark th {\n  color: #fff;\n  background-color: #343a40;\n  border-color: #454d55;\n}\n\n.table .thead-light th {\n  color: #495057;\n  background-color: #e9ecef;\n  border-color: #dee2e6;\n}\n\n.table-dark...

    *   Added `ignore_class` argument in the loss
        `SparseCategoricalCrossentropy` and metrics `IoU` and `MeanIoU`, to
        specify a class index to be ignored during loss/metric computation (e.g.
        a background/void class).
    *   Added
        [`tf.keras.models.experimental.SharpnessAwareMinimization`](https://www.tensorflow.org/api_docs/python/tf/keras/models/experimental/SharpnessAwareMinimization).