Muhammed Kocabas

Dear @pavanteja295, Thanks for your interest in our project. In our paper, PRN is the main contribution to assign keypoints to bounding box instances. We open source it for people...

Cool, so I can start with `ResNet-50+384x288`. After that I can try `ResNet-101`. I'll use `2 x 1080ti` with the default hyperparameters as in [config](https://github.com/GengDavid/pytorch-cpn/blob/master/384.288.model/config.py). Am I correct?

@GengDavid we have a little problem. `1080ti`s have 11GB memory. `batch_size=6` barely fits the memory. This means that we can train with `batch_size=12` using 2 gpus. What do you think?

I'm consistently getting OOM error, but let me check. I'll restart the computer, maybe there are some blocking processes. I'll inform you about the progress.

@GengDavid, restarting solved the problem. Thanks for pointing out! I'll update this issue as training continues. How many epochs did you train the `256x192` model?

I see, so probably it'll take 4 days to converge.

**Epoch 6** (tested with GT bboxes) ``` Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets= 20 ] = 0.688 Average Precision (AP) @[ IoU=0.50 | area= all |...

@GengDavid do you have the weights of 5th epoch of `ResNet50-256x192` model?

Yeah I saw the discussion. Please let me know about the results after modification. If you don't have enough GPUs, I can test the corrected model.

I've started to train fixed `ResNet-50+384x288` on a `Titan V` w `batch-size=24`