![photo](/responsive_image/150/150/0/0/0/cache/matlabcentral/profiles/13819614_1654064434455.jpg)
Zhiyu WANG
Followers: 0 Following: 0
C
Spoken Languages:
English
Statistics
RANK
11 441
of 297 016
REPUTATION
4
CONTRIBUTIONS
1 Question
3 Answers
ANSWER ACCEPTANCE
100.0%
VOTES RECEIVED
0
RANK
of 20 419
REPUTATION
N/A
AVERAGE RATING
0.00
CONTRIBUTIONS
0 Files
DOWNLOADS
0
ALL TIME DOWNLOADS
0
RANK
of 157 725
CONTRIBUTIONS
0 Problems
0 Solutions
SCORE
0
NUMBER OF BADGES
0
CONTRIBUTIONS
0 Posts
CONTRIBUTIONS
0 Public Channels
AVERAGE RATING
CONTRIBUTIONS
0 Highlights
AVERAGE NO. OF LIKES
Feeds
Question
is it possible to make "Sequence-to-Sequence Classification" using custom CNN network?
If so , how to create a sequence datastore and what`s the dataformat of the corresponding dlarray object?
mer än 2 år ago | 1 answer | 0
1
answerSequenceinputLayer and Convolution2dLayer
It`s recommended to transform your data to formatted dlarray objects at first. As for the dlarray object, you can refer to this...
mer än 2 år ago | 0
using predictAndUpdateState with an LSTM with featureInputLayer
LSTM requires somelike "timeseries" data while "featureInputLayer" is not along with that.Yo ucan refer to this answer: https:/...
mer än 2 år ago | 0
| accepted
Does the input size of sequenceInputLayer have to be set 1?
Becasue the input sequence data is a 1 by 10 double.It menas each time you take 1 token out of the sequence.
mer än 2 år ago | 0