guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs
Using deep stacked residual bidirectional LSTM cells (RNN) with TensorFlow, we do Human Activity Recognition (HAR). Classifying the type of movement amongst 6 categories or 18 categories on 2 different datasets.
PythonApache-2.0
Issues
- 1
sliding window error
#13 opened by nattafahhm - 0
- 4
Input 'split_dim' of 'Split' Op has type float32 that does not match expected type of int32
#11 opened by 2jungi - 3
Impressed work
#10 opened by paulcx - 1
Hello friends
#7 opened by gladuo - 0
Error when use the Bidirectional cells
#9 opened by zhaowenyi94 - 3
question about tf.get_variable()
#3 opened by zhaoyu611