out of memory

[heiyuxiaokai]

File "/home/fw/Softwares/FCOS/maskrcnn_benchmark/structures/boxlist_ops.py", line 84, in boxlist_iou
wh = (rb - lt + TO_REMOVE).clamp(min=0) # [N,M,2]
RuntimeError: CUDA out of memory. Tried to allocate 1.56 GiB (GPU 1; 11.92 GiB total capacity; 7.99 GiB already allocated; 1.20 GiB free; 1.74 GiB cached)

It seems the iou caculate' problem. I use retinanet, batch 4, 2 titan x(12G)
The GPU use of beginning:

Should I set the batch to 2?

[tianzhi0549]

@heiyuxiaokai Did FCOS run out of memory?

[heiyuxiaokai]

@tianzhi0549 No，Maybe the iou caculate process of a special image（with many boxes） need a lot of memory. FCOS haven't this process. Did your GPU is 12G where you train this model for (4 gpu, batch 8)?
The data I use is remote sensing image, which may have many object.

[tianzhi0549]

@heiyuxiaokai our GPUs are 32GB V100.

[heiyuxiaokai]

@tianzhi0549 So I should set batch to 2. You train batch 8 of 4 GPU(V100). Why don't you use a larger batch for 32g GPU?

[tianzhi0549]

@heiyuxiaokai We use 16 images in a mini-batch for a fair comparison.

[heiyuxiaokai]

Too many GT Boxes. It was explained there.
facebookresearch/maskrcnn-benchmark#18

[dreamhighchina]

你的解决了吗？我也是在计算loss的时候出错了，我的batchsize是2都错。

[heiyuxiaokai]

@dreamhighchina Reference there: facebookresearch/maskrcnn-benchmark#884