Mark Sinton
Hi, I notice in previous commits you have functionality to initialise the encoder weights from a pre-trained VGG16, but this does not appear to be in the latest version. Why...
In mobilenetv2.py: ``` def blocks(net, expansion, output_filters, repeat, stride): input_filters = net.shape[3].value # first layer should take stride into account net = block(net, input_filters, output_filters, expansion, stride) for _ in...
Make Maven repository configurable via an env var, default to public Maven repo *Issue number:* #209 *Description of changes:* Currently `python setup.py download_jars` is hardcoded to download the KCL jars...
Currently `python setup.py download_jars` is hardcoded to download the KCL jars from the public Maven repository [https://search.maven.org](https://search.maven.org) ``` def package_url(self, group_id, artifact_id, version): # # Sample url: # https://search.maven.org/remotecontent?filepath=org/apache/httpcomponents/httpclient/4.2/httpclient-4.2.jar #...
In the [sample code](https://github.com/awslabs/amazon-kinesis-client-python/blob/master/samples/sample_kclpy_app.py), when a shutdown is requested we call the `checkpoint()` method with no args, which means the checkpoint sequence number will be the end of the most...
In the paper you say that you add a safety loss term, that penalizes all predicted states of vehicles that lie in an obstacle cell. In the args.txt file supplied...
In order to predict multiple time steps ahead for the training/validation/testing where you already have access to the future intermediate representations you simply combine the prediction at the previous time...