-
Notifications
You must be signed in to change notification settings - Fork 6.8k
object location and detection #214
Comments
Same question here. |
I will add feature to write handcraft kernel directly in op, and we always welcome you to send PR to contribute to MXNet |
@antinucleon Thanks! |
Fast and Faster R-CNN's changes to Caffe are all in this commit and the object detection application is here.
|
Any chance to add layers which are required by faster-rcnn in near future? |
are there any plans for a faster-rcnn type example in the image-classification section? This would be greatly appreciated, if possible. |
New operator import mxnet as mx
data = mx.sym.Variable('data')
# [batch_size, channel, height, width]
rois = mx.sym.Variable('rois')
# [roi_number, 5]
# last dimension is [batch index of image, x1, y1, x2, y2]
# some convolutional layer
roi_pool = mx.sym.ROIPooling(data=data, rois=rois, pooled_size=(6, 6), spatial_scale=0.0625)
# please note that batch_size changes from batch_size to roi_number after ROI pooling. |
@precedenceguo How to train network with |
I noticed that the executor_manager.DataParallelExecutorGroup uses the same |
Multiple devices training split data into slices for devices. In this example, each data batch has image shape |
I'm not using multiple devices for training. I use the python api |
There could exist some issue about varying batch size with the FeedForward API. Is there any error message or anomaly? |
HI,
fast-rcnn or fcatser-rcnn is a very useful application. Both are implemented and trained in Caffe framework.
Is there a way to import its network model and pretrained model to mxnet? If not. do you have a plan to use mxnet to implement fast-rcnn or faster-rcnn?
Thanks,
Kaishi
The text was updated successfully, but these errors were encountered: