[BUG] Fixed numpy implementation of activator

Author: Leguark

gempy_engine/modules/activator/activator_interface.py

@@ -177,11 +177,11 @@ def _final_faults_segmentation(Z, edges, sigmoid_slope):
 def _lith_segmentation(Z, edges, ids, sigmoid_slope):
     # 1) per-edge temperatures τ_k = |Δ_k|/(4·m)
     jumps = np.abs(ids[1:] - ids[:-1])  # shape (K-1,)
-    tau_k = jumps / (4 * sigmoid_slope)  # shape (K-1,)
+    tau_k = jumps / float(4 * sigmoid_slope)  # shape (K-1,)
     # 2) first bin (-∞, e1) via σ((e1 - Z)/τ₁)
     first = _sigmoid(
-        scalar_field=Z,
-        edges=edges[0],
+        scalar_field=-Z,
+        edges=-edges[0],
         tau_k=tau_k[0]
     )  # shape (...,)
     # 3) last  bin [e_{K-1}, ∞) via σ((Z - e_{K-1})/τ_{K-1})
@@ -213,4 +213,4 @@ def _lith_segmentation(Z, edges, ids, sigmoid_slope):
 
 
 def _sigmoid(scalar_field, edges, tau_k):
-    return 1.0 / (1.0 + np.exp((scalar_field - edges) / tau_k))
+    return 1.0 / (1.0 + np.exp(-(scalar_field - edges) / tau_k))

tests/test_common/test_modules/test_activator_fns.py

@@ -56,6 +56,46 @@ def test_activator_3_layers_segmentation_function(simple_model_3_layers, simple_
         _plot_continious(grid, ids_block, interpolation_input)
 
 
+def test_activator_3_layers_segmentation_function_II(simple_model_3_layers, simple_grid_3d_more_points_grid):
+    interpolation_input = simple_model_3_layers[0]
+    options = simple_model_3_layers[1]
+    data_shape = simple_model_3_layers[2].tensors_structure
+    grid = dataclasses.replace(simple_grid_3d_more_points_grid)
+    interpolation_input.set_temp_grid(grid)
+
+    interp_input: SolverInput = input_preprocess(data_shape, interpolation_input)
+    weights = _solve_interpolation(interp_input, options.kernel_options)
+
+    exported_fields = _evaluate_sys_eq(interp_input, weights, options)
+    exported_fields.set_structure_values(
+        reference_sp_position=data_shape.reference_sp_position,
+        slice_feature=interpolation_input.slice_feature,
+        grid_size=interpolation_input.grid.len_all_grids)
+
+    Z_x: np.ndarray = exported_fields.scalar_field
+    sasp = exported_fields.scalar_field_at_surface_points
+    ids = np.array([1, 2, 3, 4])
+
+    print(Z_x, Z_x.shape[0])
+    print(sasp)
+
+    BackendTensor.change_backend_gempy(AvailableBackends.numpy)
+    ids_block = activate_formation_block(
+        exported_fields=exported_fields,
+        ids=ids,
+        sigmoid_slope=500 * 4
+    )[0, :-7]
+
+    BackendTensor.change_backend_gempy(AvailableBackends.numpy)
+    if BackendTensor.engine_backend == AvailableBackends.PYTORCH:
+        ids_block = ids_block.detach().numpy()
+        Z_x = Z_x.detach().numpy()
+        interpolation_input.surface_points.sp_coords = interpolation_input.surface_points.sp_coords.detach().numpy()
+
+    if plot:
+        _plot_continious(grid, ids_block, interpolation_input)
+
+
 def _plot_continious(grid, ids_block, interpolation_input):
     block__ = ids_block[grid.dense_grid_slice]
     unique = np.unique(block__)