wishforgood
wishforgood
I used the default setting(which I think is Densenet-12-BC with data augmentation) on cifar-100(via just changing the name of `dataset `class and the `nClasses `variable). The training curve looks like...
DD不光需要看直播，第一时间看到动态更新也是很重要的需求，希望能有跟开播提醒一样提醒一下动态更新的功能。
I'm trying to connect to my docker container through x2go remote desktop. So I use docker-ssh as a ssh server to help ssh into the container. However, after type into...
I wonder from which version of Visual Genome are the frequent objects and relationships selected. Because I counted the occurrences myself but got totally different results as in [VG-SGG-dicts.json](http://cvgl.stanford.edu/scene-graph/dataset/VG-SGG-dicts.json). For...
I used cgi-bin/cgi_exe.py and feed my example image to it. While I expect a similar performance, I got totally unrecognizable results. Here is my example image, the corresponding result and...
## ❓ Questions and Help **What I have done:** I set MODEL.ROI_RELATION_HEAD.PREDICTOR to be VCTreePredictor, and set the CONTEXT_HIDDEN_DIM in configs/e2e_relation_X_101_32_8_FPN_1x.yaml to be 1024. Following Training Example 1, I gave...
**What I have done:** I have downloaded your data from https://drive.google.com/file/d/1_ObEsWHHOrzAwLf5OvdY-64r3Ne4nTcR/view?usp=sharing. Then I run the code train_graph_VG and test_graph_VG to get the predictions. I followed the order in file "torchdata/pruned_graph_cocosplit.t7"...
Hello, I'm interested in this work and want to try it. Could you please provide the version of python packages like pytorch in the environment?
I git cloned the code and ran it with the command suggested by readme. However, the Top1 acc stopped at 76% after 160 epochs. I've seen the learning curve in...
There are some papers using sub-graph proposal instead of relation proposal. However, they perform experiments on other subset of Visual Genome, and is hard to compared with the methods mentioned...