diff --git a/src/Activation.cpp b/src/Activation.cpp
index cf09b3d..2ee971e 100644
--- a/src/Activation.cpp
+++ b/src/Activation.cpp
@@ -14,12 +14,14 @@ Activation::Activation(Network *net, dataDim_t input_dim, tkdnnActivationMode_t
     checkCUDNN( cudnnSetTensor4dDescriptor(srcTensorDesc,
                                         net->tensorFormat,
                                         net->dataType,
-                                        input_dim.n, input_dim.c,
+                                        input_dim.n*input_dim.l, 
+                                        input_dim.c,
                                         input_dim.h, input_dim.w) );
     checkCUDNN( cudnnSetTensor4dDescriptor(dstTensorDesc,
                                             net->tensorFormat,
                                             net->dataType,
-                                            input_dim.n, input_dim.c,
+                                            input_dim.n*input_dim.l, 
+                                            input_dim.c,
                                             input_dim.h, input_dim.w) );
 }
 
diff --git a/tests/simple_dense.py b/tests/simple_dense.py
index 14af613..0e652cf 100644
--- a/tests/simple_dense.py
+++ b/tests/simple_dense.py
@@ -13,12 +13,13 @@ from weights_exporter import *
 def dense_model():
     model = Sequential()
 
-    model.add(Reshape((10, 10, 1), input_shape=(10, 10)))
-    model.add(Convolution2D(2, (4, 4), subsample=(2, 2), 
+    model.add(Reshape((10, 10, 4, 1), input_shape=(10, 10, 4)))
+    model.add(Convolution3D(2, (4, 4, 2), subsample=(2, 2, 1), activation="relu",
+                           bias_initializer='random_uniform'))
+    model.add(Convolution3D(4, (2, 2, 2), subsample=(1, 1, 1), 
                            bias_initializer='random_uniform'))
     model.add(ELU())
-    model.add(Convolution2D(4, (2, 2), subsample=(1, 1), 
-                           bias_initializer='random_uniform', activation="relu"))
+
     sgd = keras.optimizers.Adam(lr=1e-4, decay=1e-8)
     model.compile(optimizer=sgd, loss="mse")
     return model
@@ -29,10 +30,10 @@ if __name__ == '__main__':
 
     model = dense_model()
     wg = model.get_weights()
-    export_conv2d("conv0", wg[0], wg[1])
-    export_conv2d("conv1", wg[2], wg[3])
+    export_conv3d("conv0", wg[0], wg[1])
+    export_conv3d("conv1", wg[2], wg[3])
 
-    grid = np.random.rand(10,10)
+    grid = np.random.rand(10,10,4)
     X = grid[None,:,:]
     i = np.array(grid.flatten(), dtype=np.float32)
     print i
diff --git a/tests/test.cpp b/tests/test.cpp
index 3c24101..1ba5027 100644
--- a/tests/test.cpp
+++ b/tests/test.cpp
@@ -13,11 +13,11 @@ int main() {
 
     // Network layout
     tkDNN::Network net;
-    tkDNN::dataDim_t dim(1, 1, 10, 10);
-    tkDNN::Conv2d     c0 (&net, dim,           2, 4, 4, 2, 2, c0_bin, c0_bias_bin);
-    tkDNN::Activation a0 (&net, c0.output_dim, tkDNN::ACTIVATION_ELU);
-    tkDNN::Conv2d     c1 (&net, a0.output_dim, 4, 2, 2, 1, 1, c1_bin, c1_bias_bin);
-    tkDNN::Activation a1 (&net, c1.output_dim, tkDNN::ACTIVATION_RELU);
+    tkDNN::dataDim_t dim(1, 1, 10, 10, 4);
+    tkDNN::Conv3d     c0 (&net, dim,           2, 4, 4, 2, 2, 2, 1, c0_bin, c0_bias_bin);
+    tkDNN::Activation a0 (&net, c0.output_dim, tkDNN::ACTIVATION_RELU);
+    tkDNN::Conv3d     c1 (&net, a0.output_dim, 4, 2, 2, 2, 1, 1, 1, c1_bin, c1_bias_bin);
+    tkDNN::Activation a1 (&net, c1.output_dim, tkDNN::ACTIVATION_ELU);
 
     // Load input
     value_type *data;