Model: "encoder_r1" __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== input_1 (InputLayer) [(None, 4096, 3)] 0 __________________________________________________________________________________________________ shared_conv_0 (Conv1D) (None, 1024, 64) 9472 input_1[0][0] __________________________________________________________________________________________________ shared_conv_0_batchnorm (BatchN (None, 1024, 64) 256 shared_conv_0[0][0] __________________________________________________________________________________________________ leaky_re_lu (LeakyReLU) multiple 0 shared_conv_0_batchnorm[0][0] r1_dense_1_batchnorm[0][0] r1_dense_2_batchnorm[0][0] r1_dense_3_batchnorm[0][0] __________________________________________________________________________________________________ max_pooling1d (MaxPooling1D) (None, 254, 64) 0 leaky_re_lu[0][0] __________________________________________________________________________________________________ cfg0_conv (Functional) (None, 254, 256) 76928 max_pooling1d[0][0] __________________________________________________________________________________________________ cfg0_identity_p1 (Functional) (None, 254, 256) 71552 cfg0_conv[0][0] cfg0_identity_p1[0][0] __________________________________________________________________________________________________ cfg1_conv (Functional) (None, 64, 512) 383232 cfg0_identity_p1[1][0] __________________________________________________________________________________________________ cfg1_identity_p1 (Functional) (None, 64, 512) 282368 cfg1_conv[0][0] cfg1_identity_p1[0][0] cfg1_identity_p1[1][0] __________________________________________________________________________________________________ cfg2_conv (Functional) (None, 16, 1024) 1520128 cfg1_identity_p1[2][0] __________________________________________________________________________________________________ cfg2_identity_p1 (Functional) (None, 512, 1024) 1121792 cfg2_conv[0][0] cfg2_identity_p1[0][0] cfg2_identity_p1[1][0] cfg2_identity_p1[2][0] cfg2_identity_p1[3][0] __________________________________________________________________________________________________ cfg3_conv (Functional) (None, 4, 2048) 6054912 cfg2_identity_p1[4][0] __________________________________________________________________________________________________ cfg3_identity_p1 (Functional) (None, 1024, 2048) 4471808 cfg3_conv[0][0] cfg3_identity_p1[0][0] __________________________________________________________________________________________________ average_pooling1d (AveragePooli (None, 1, 2048) 0 cfg3_identity_p1[1][0] __________________________________________________________________________________________________ dropout (Dropout) (None, 1, 2048) 0 average_pooling1d[0][0] __________________________________________________________________________________________________ flatten (Flatten) (None, 2048) 0 dropout[0][0] __________________________________________________________________________________________________ flatten_1 (Flatten) (None, 2048) 0 flatten[0][0] __________________________________________________________________________________________________ r1_dense_1 (Dense) (None, 1024) 2098176 flatten_1[0][0] __________________________________________________________________________________________________ r1_dense_1_batchnorm (BatchNorm (None, 1024) 4096 r1_dense_1[0][0] __________________________________________________________________________________________________ r1_dense_2 (Dense) (None, 1024) 1049600 leaky_re_lu[1][0] __________________________________________________________________________________________________ r1_dense_2_batchnorm (BatchNorm (None, 1024) 4096 r1_dense_2[0][0] __________________________________________________________________________________________________ r1_dense_3 (Dense) (None, 1024) 1049600 leaky_re_lu[2][0] __________________________________________________________________________________________________ r1_dense_3_batchnorm (BatchNorm (None, 1024) 4096 r1_dense_3[0][0] __________________________________________________________________________________________________ r1_mean_dense (Dense) (None, 20) 20500 leaky_re_lu[3][0] __________________________________________________________________________________________________ r1_logvar_dense (Dense) (None, 20) 20500 leaky_re_lu[3][0] __________________________________________________________________________________________________ r1_modes_dense (Dense) (None, 10) 10250 leaky_re_lu[3][0] __________________________________________________________________________________________________ concatenate (Concatenate) (None, 50) 0 r1_mean_dense[0][0] r1_logvar_dense[0][0] r1_modes_dense[0][0] ================================================================================================== Total params: 18,253,362 Trainable params: 18,216,370 Non-trainable params: 36,992 __________________________________________________________________________________________________ Model: "encoder_q" __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== input_1 (InputLayer) [(None, 4096, 3)] 0 __________________________________________________________________________________________________ shared_conv_0 (Conv1D) (None, 1024, 64) 9472 input_1[0][0] __________________________________________________________________________________________________ shared_conv_0_batchnorm (BatchN (None, 1024, 64) 256 shared_conv_0[0][0] __________________________________________________________________________________________________ leaky_re_lu (LeakyReLU) multiple 0 shared_conv_0_batchnorm[0][0] q_dense_1_batchnorm[0][0] q_dense_2_batchnorm[0][0] q_dense_3_batchnorm[0][0] __________________________________________________________________________________________________ max_pooling1d (MaxPooling1D) (None, 254, 64) 0 leaky_re_lu[0][0] __________________________________________________________________________________________________ cfg0_conv (Functional) (None, 254, 256) 76928 max_pooling1d[0][0] __________________________________________________________________________________________________ cfg0_identity_p1 (Functional) (None, 254, 256) 71552 cfg0_conv[0][0] cfg0_identity_p1[0][0] __________________________________________________________________________________________________ cfg1_conv (Functional) (None, 64, 512) 383232 cfg0_identity_p1[1][0] __________________________________________________________________________________________________ cfg1_identity_p1 (Functional) (None, 64, 512) 282368 cfg1_conv[0][0] cfg1_identity_p1[0][0] cfg1_identity_p1[1][0] __________________________________________________________________________________________________ cfg2_conv (Functional) (None, 16, 1024) 1520128 cfg1_identity_p1[2][0] __________________________________________________________________________________________________ cfg2_identity_p1 (Functional) (None, 512, 1024) 1121792 cfg2_conv[0][0] cfg2_identity_p1[0][0] cfg2_identity_p1[1][0] cfg2_identity_p1[2][0] cfg2_identity_p1[3][0] __________________________________________________________________________________________________ cfg3_conv (Functional) (None, 4, 2048) 6054912 cfg2_identity_p1[4][0] __________________________________________________________________________________________________ cfg3_identity_p1 (Functional) (None, 1024, 2048) 4471808 cfg3_conv[0][0] cfg3_identity_p1[0][0] __________________________________________________________________________________________________ average_pooling1d (AveragePooli (None, 1, 2048) 0 cfg3_identity_p1[1][0] __________________________________________________________________________________________________ dropout (Dropout) (None, 1, 2048) 0 average_pooling1d[0][0] __________________________________________________________________________________________________ input_2 (InputLayer) [(None, 2)] 0 __________________________________________________________________________________________________ flatten (Flatten) (None, 2048) 0 dropout[0][0] __________________________________________________________________________________________________ flatten_2 (Flatten) (None, 2) 0 input_2[0][0] __________________________________________________________________________________________________ concatenate_1 (Concatenate) (None, 2050) 0 flatten[0][0] flatten_2[0][0] __________________________________________________________________________________________________ flatten_3 (Flatten) (None, 2050) 0 concatenate_1[0][0] __________________________________________________________________________________________________ q_dense_1 (Dense) (None, 1024) 2100224 flatten_3[0][0] __________________________________________________________________________________________________ q_dense_1_batchnorm (BatchNorma (None, 1024) 4096 q_dense_1[0][0] __________________________________________________________________________________________________ q_dense_2 (Dense) (None, 1024) 1049600 leaky_re_lu[4][0] __________________________________________________________________________________________________ q_dense_2_batchnorm (BatchNorma (None, 1024) 4096 q_dense_2[0][0] __________________________________________________________________________________________________ q_dense_3 (Dense) (None, 1024) 1049600 leaky_re_lu[5][0] __________________________________________________________________________________________________ q_dense_3_batchnorm (BatchNorma (None, 1024) 4096 q_dense_3[0][0] __________________________________________________________________________________________________ q_mean_dense (Dense) (None, 2) 2050 leaky_re_lu[6][0] __________________________________________________________________________________________________ q_logvar_dense (Dense) (None, 2) 2050 leaky_re_lu[6][0] __________________________________________________________________________________________________ concatenate_2 (Concatenate) (None, 4) 0 q_mean_dense[0][0] q_logvar_dense[0][0] ================================================================================================== Total params: 18,208,260 Trainable params: 18,171,268 Non-trainable params: 36,992 __________________________________________________________________________________________________ Model: "decoder_r2" __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== input_1 (InputLayer) [(None, 4096, 3)] 0 __________________________________________________________________________________________________ shared_conv_0 (Conv1D) (None, 1024, 64) 9472 input_1[0][0] __________________________________________________________________________________________________ shared_conv_0_batchnorm (BatchN (None, 1024, 64) 256 shared_conv_0[0][0] __________________________________________________________________________________________________ leaky_re_lu (LeakyReLU) multiple 0 shared_conv_0_batchnorm[0][0] r2_dense_1_batchnorm[0][0] r2_dense_2_batchnorm[0][0] r2_dense_3_batchnorm[0][0] __________________________________________________________________________________________________ max_pooling1d (MaxPooling1D) (None, 254, 64) 0 leaky_re_lu[0][0] __________________________________________________________________________________________________ cfg0_conv (Functional) (None, 254, 256) 76928 max_pooling1d[0][0] __________________________________________________________________________________________________ cfg0_identity_p1 (Functional) (None, 254, 256) 71552 cfg0_conv[0][0] cfg0_identity_p1[0][0] __________________________________________________________________________________________________ cfg1_conv (Functional) (None, 64, 512) 383232 cfg0_identity_p1[1][0] __________________________________________________________________________________________________ cfg1_identity_p1 (Functional) (None, 64, 512) 282368 cfg1_conv[0][0] cfg1_identity_p1[0][0] cfg1_identity_p1[1][0] __________________________________________________________________________________________________ cfg2_conv (Functional) (None, 16, 1024) 1520128 cfg1_identity_p1[2][0] __________________________________________________________________________________________________ cfg2_identity_p1 (Functional) (None, 512, 1024) 1121792 cfg2_conv[0][0] cfg2_identity_p1[0][0] cfg2_identity_p1[1][0] cfg2_identity_p1[2][0] cfg2_identity_p1[3][0] __________________________________________________________________________________________________ cfg3_conv (Functional) (None, 4, 2048) 6054912 cfg2_identity_p1[4][0] __________________________________________________________________________________________________ cfg3_identity_p1 (Functional) (None, 1024, 2048) 4471808 cfg3_conv[0][0] cfg3_identity_p1[0][0] __________________________________________________________________________________________________ average_pooling1d (AveragePooli (None, 1, 2048) 0 cfg3_identity_p1[1][0] __________________________________________________________________________________________________ dropout (Dropout) (None, 1, 2048) 0 average_pooling1d[0][0] __________________________________________________________________________________________________ input_3 (InputLayer) [(None, 2)] 0 __________________________________________________________________________________________________ flatten (Flatten) (None, 2048) 0 dropout[0][0] __________________________________________________________________________________________________ flatten_4 (Flatten) (None, 2) 0 input_3[0][0] __________________________________________________________________________________________________ concatenate_3 (Concatenate) (None, 2050) 0 flatten[0][0] flatten_4[0][0] __________________________________________________________________________________________________ flatten_5 (Flatten) (None, 2050) 0 concatenate_3[0][0] __________________________________________________________________________________________________ r2_dense_1 (Dense) (None, 1024) 2100224 flatten_5[0][0] __________________________________________________________________________________________________ r2_dense_1_batchnorm (BatchNorm (None, 1024) 4096 r2_dense_1[0][0] __________________________________________________________________________________________________ r2_dense_2 (Dense) (None, 1024) 1049600 leaky_re_lu[7][0] __________________________________________________________________________________________________ r2_dense_2_batchnorm (BatchNorm (None, 1024) 4096 r2_dense_2[0][0] __________________________________________________________________________________________________ r2_dense_3 (Dense) (None, 1024) 1049600 leaky_re_lu[8][0] __________________________________________________________________________________________________ r2_dense_3_batchnorm (BatchNorm (None, 1024) 4096 r2_dense_3[0][0] __________________________________________________________________________________________________ JointVonMisesFisher_mean (Dense (None, 3) 3075 leaky_re_lu[9][0] __________________________________________________________________________________________________ JointVonMisesFisher_logvar (Den (None, 1) 1025 leaky_re_lu[9][0] __________________________________________________________________________________________________ concatenate_4 (Concatenate) (None, 4) 0 JointVonMisesFisher_mean[0][0] JointVonMisesFisher_logvar[0][0] ================================================================================================== Total params: 18,208,260 Trainable params: 18,171,268 Non-trainable params: 36,992 __________________________________________________________________________________________________