How to pass In-memory Object to Watson Visual Recognition service using Python SDK

Question

I am using IBM data Science Experience notebooks to create a custom classifier for the visual recognition service. I have the training zip files loaded into Object storage. But when I try to create the custom classifier it fails with the error message

"explanation": "Cannot execute learning task : Could not train classifier. Verify there are at least 10 positive training images for at least 1 class and at least 10 other unique training images."

I am using Swiftclient to access the object storage and then converting the contents to BytesIO to pass it to create_classifier function

conn = swiftclient.Connection(
    key=credentials['password'],
    authurl=credentials['auth_url']+"/v3",
    auth_version='3',
    os_options={
        "project_id": credentials['project_id'],
        "user_id": credentials['user_id'],
        "region_name": credentials['region']})

Class1 = conn.get_object(credentials['container'],'imageset1.zip')
Class2 =  conn.get_object(credentials['container'], 'imageset2.zip')
Class3 = conn.get_object(credentials['container'], 'imageset3.zip')