Modifying the figures to be published

app.py

@@ -320,6 +320,7 @@ latent_matrix = np.array(latent_matrix).T  # Transposes the matrix so that each
 # Plotting the Interpolation in 2D Using Chosen Points
 if st.button("Generate Interpolation:"):
     plt.figure(2)
+    """
     plot_rows = 2
     plot_columns = num_interp + 2
 
@@ -340,5 +341,46 @@ if st.button("Generate Interpolation:"):
     plt.subplot(plot_rows, plot_columns, num_interp + 2), plt.imshow(number_2, cmap='gray', vmin=0, vmax=1)
     # plt.title("Second Interpolation Point:\n" + str(box_shape_test[number_2]) + "\nPixel Density: " + str(
     #             box_density_test[number_2]) + "\nAdditional Pixels: " + str(additional_pixels_test[number_2]))  # + "\nPredicted Latent Point 2: " + str(latent_point_2)
+    """
+    linear_interp_latent = np.linspace(latent_point_1, latent_point_2, interp_length)
+    print(len(linear_interp_latent))
+
+    linear_predicted_interps = []
+    figure = np.zeros((28 * num_interp, 28))
+    for i in range(num_interp):
+        generated_image = decoder_model_boxes.predict(np.array([linear_interp_latent[i]]))[0]
+        figure[i * 28:(i + 1) * 28, 0:28, ] = generated_image[:, :, -1]
+        linear_predicted_interps.append(generated_image[:, :, -1])
+
+    plt.figure(figsize=(15, 15))
+    plt.imshow(figure, cmap='gray')
+
+    '''
+    latent_matrix_2 = []  # This will contain the latent points of the interpolation
+    for column in range(latent_dimensionality):
+        new_column = np.linspace(latent_point_3[column], latent_point_4[column], num_interp)
+        latent_matrix_2.append(new_column)
+    latent_matrix_2 = np.array(latent_matrix_2).T  # Transposes the matrix so that each row can be easily indexed
+
+    mesh = []  # This will create a mesh by interpolating between the two interpolations
+    for column in range(num_interp):
+        row = np.linspace(latent_matrix[column], latent_matrix_2[column], num_interp)
+        mesh.append(row)
+
+    mesh = np.transpose(mesh, axes=(1, 0, 2))  # Transpose the array so it matches the original interpolation
+    generator_model = decoder_model_boxes
+
+    figure = np.zeros((28 * num_interp, 28 * num_interp))
+
+    mesh_predicted_interps = []
+    for i in range(num_interp):
+        for j in range(num_interp):
+            generated_image = generator_model.predict(np.array([mesh[i][j]]))[0]
+            figure[i * 28:(i + 1) * 28, j * 28:(j + 1) * 28, ] = generated_image[:, :, -1]
+            mesh_predicted_interps.append(generated_image[:, :, -1])
+    
+    plt.figure(figsize=(15, 15))
+    plt.imshow(figure, cmap='gray')
+    '''
     plt.figure(2)
     st.pyplot(plt.figure(2))