GCNet
GCNet copied to clipboard
xvjiarui
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
Using the best setting of GC-ResNet50 and train it from scratch on ImageNet, I found it will be stuck in a high loss in the early epochs before the training...
in the mmdet/ops/gcb/ContextBlock line 28 self.planes = int(inplanes * ratio) this * Should change it to // ？
hello， in your paper，you first visualize the attention maps for different query positions. can you give me some help. i do not know how to visualize the attention maps for...
Hello, thank you very much for your work, I noticed that your GCNet is 2D, but nonlocal is from 1D to 3D. Do you have 1D code?
Hello,can I change the model in faster-rcnn resnet instead of mask rcnn only by change this demo? //--------------------------------------------------------------------------------------------------------------------- model settings model = dict( type='FasterRCNN', pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0,...
Hi, Thanks for your great work! In your paper, attention maps of particular query points are shown. Could you share this visualization code? More specifically, did you implement an interactive...
Supposed I want to get benchmark using GCNet but only object detection on my custom dataset, do I need to have mask for trainging or just bounding box is enough?
Do you verified your idea in 3D model? Or in 3D data, dose the attention value of every point is still the same?
Hello, Is it possible to view Attention maps at different query positions ? If yes, how can we do it?
Hello, I'm not sure if GCNet in mmdetection use ImageNet pretrained model (specifically GCNet + ResNet pretrained model) cause I saw in the GCNet/config, it only uses standard "torchvision://resnet50" in...
