Open blessedlex opened 3 years ago
For a training size of 5,000: th train.lua
For a training size of 4,000: th train.lua -batch 25
For a training size of 1,000: th train.lua -batch 7
For evaluating each model: th evalPerImage.lua /model/path
For a training size of 100%: train_nGPU=1 ./scripts/train_multipathnet_coco.sh
For a training size of 80%: train_nGPU=1 batchSize=51 ./scripts/train_multipathnet_coco.sh
For a training size of 20%: train_nGPU=1 batchSize=13 ./scripts/train_multipathnet_coco.sh
For evaluation: test_nGPU=1 test_nsamples=5000 ./scripts/eval_coco.sh
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.244 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.402 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.268 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.078 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.266 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.394 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.249 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.368 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.377 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.135 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.444 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.561
findings posted here