ThomasDelteil commented on issue #7946: Defining Residual Convolution Structures in Block from gluon Module URL: https://github.com/apache/incubator-mxnet/issues/7946#issuecomment-402569038 @SumNeuron glancing quickly through the issue it seems that you want to format your data in the following way `(N, C, T)` where `N` is the batch size, `C` the number of channels and `T` the length of signal time window (sometimes called `W` for width of your signal). For example, for 3 channels and 64 measurements, using 32 convolutions kernels: ```python N = 1 T = 64 C = 3 signal = mx.nd.ones((N, C, T)) conv1D = mx.gluon.nn.Conv1D(channels=32, kernel_size=3) conv1D.initialize() out = conv1D(signal) out.shape (1, 32, 62) ``` To answer your second question, have a look at GluonCV where you can find an implementation of Faster-RCNN and SSD. - [Faster-RCNN](https://gluon-cv.mxnet.io/build/examples_detection/train_ssd_voc.html#sphx-glr-build-examples-detection-train-ssd-voc-py) - [SSD](https://gluon-cv.mxnet.io/build/examples_detection/train_ssd_voc.html) @SumNeuron if you would like to follow up, please create a post on https://discuss.mxnet.io, thanks! @szha could you please close the issue? Thanks!
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
