Yilun Chen
Yilun Chen
I dont tried it. But I think it should hurt the performance. But Google also use the resnet with dilation in coco2016 competition. The performance is also compared in the...
1. Whether pre-trained ResNet helps or not, the improvement above it is our contribution. 2. We compare our model with ResNet and hourglass network under same training configuration in our...
The ensemble strategy is using the average heatmap from different models as the final heatmap.
Your result is similar to #11 . I think there is something wrong while testing. I found your testing images are 40504 unique images. We test the results on the...
COCO 2014 minival json and its detection result json is provided.
Almost same. It might has some difference when sync-bn is used.
No. Generally I think the performance between them are same. But it should be validated by experiments.
Hi, As I just finished the paper submission for the ICCV deadline, I will check the config in these two days. The monocular configs need some extra modifications. I remembered...
It looks like you did not load the model weight well. Please check the output result txt first. And then check if the model weights are loaded well.
Hi, can you show me the inference results and the log? In my old environment the results should be correct. Note that there could be some warning during loading the...