I am trying char modelling in LSTM s and referring to the dl4j example in github -
/* *****************************************************************************
*
*
*
* This program and the accompanying materials are made available under the
* terms of the Apache License, Version 2.0 which is available at
* https://www.apache.org/licenses/LICENSE-2.0.
* See the NOTICE file distributed with this work for additional
* information regarding copyright ownership.
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations
* under the License.
*
* SPDX-License-Identifier: Apache-2.0
******************************************************************************/
package org.deeplearning4j.examples.advanced.modelling.charmodelling.generatetext;
show original
I would like to know if it is desirable to provide input to an embedding sequence layer , instead of directly providing to LSTM … , if possible how to provide the time dimension in the embedding ? (any example for the same is appreciated )
jijiji
May 27, 2021, 10:55am
2
Check input shape description. It might contain data you’re looking for depend on a layer type.