From: A novel human activity recognition architecture: using residual inception ConvLSTM layer
Layer ID | Layer name | Input size | Output size | Number of parameters | Input ID | Return sequence |
---|---|---|---|---|---|---|
system_input | Input | (16, 20, 40, 40, 1) | (16, 20, 40, 40, 1) | 0 | - | - |
convlstm_m_1 | ConvLSTM | (16, 20, 40, 40, 1) | (16, 20, 40, 40, 24) | 21,696 | system_input | Yes |
batch_norm_1 | Batch Normalization | (16, 20, 40, 40, 24) | (16, 20, 40, 40, 24) | 96 | convlstm_m_1 | - |
resincconvlstm | ResIncConvLSTM | (16, 20, 40, 40, 24) | (16, 20, 40, 40, 24) | 19,760 | batch_norm_1 | No |
convlstm_m_2 | ConvLSTM | (16, 20, 40, 40, 24) | (16, 40, 40, 1) | 904 | resincconvlstm | No |
batch_norm_2 | Batch Normalization | (16, 40, 40, 1) | (16, 40, 40, 1) | 4 | convlstm_m_2 | - |
reshape | Reshape | (16, 40, 40, 1) | (16, 1, 1600) | 0 | batch_norm_2 | - |
dense_1 | Dense | (16, 1, 1600) | (16, 1, 6) | 9606 | reshape | - |
dropout | Dropout | (16, 1, 6) | (16, 1, 6) | 0 | dense_1 | - |
dense_1 | Dense | (16, 1, 6) | (16, 1, 6) | 42 | dropout | - |