You can load your data as numpy array (.npy format) and use flow method instead of flow_from_directory. Colab provides 25GB RAM ,so even for big data-sets you can load your entire data into memory. The speed up was found to be aroud 2.5x, with the same data generation steps!!!(Even faster than data stored in colab local disk i.e '/content' or google drive.
Google Colab instances are using some faster memory than google drive. As you are accessing files from google drive (it has a larger access time) so you are getting low speed. First copy the files to colab instance then train your network. 2b1af7f3a8