Detectron.pytorch

Detectron.pytorch copied to clipboard

Can we have batch size > 1 for inference?

4

Hi, when I run tools/test_net.py, I realize there is no place to set up batch size during inference. 1. Does the default batch size = 1? I assume the image...

nymph332088

Is the NMS soft NMS？

3

Is the NMS soft NMS？

engineer1109

Could not train on v100

4

## PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING 1. **Read the README.md thoroughly ! README.md is not a decoration.** 2. Please search existing *open and closed* issues in case your issue...

qinhaifangpku

I think that RPN_PRE_NMS_TOP_N is not per image unless IMS_PER_BATCH = 1. Is it a bug?

wwn1233

This is a PR to support [RetinaNet](https://arxiv.org/abs/1708.02002), a state-of-the-art one-stage object detector. The model (ResNet 50 with 800 pixels) achieved AP of 35.3 instead of 35.7 reported on the paper....

miliadis

Error : " if 'blobs' in src_blobs: TypeError: argument of type 'int' is not iterable" I have been using detectron, but I have been using the load_ckpt method. I have...

B2Gdevs

Training with a custom dataset

4

Can anyone suggest how can we train this model from scratch using a custom dataset other than COCO. Like how to prepare data and the steps involved in training? Thanks

vsd550

Hanhanhan11

Memory grows with less TEST.SCALE

1

Hi, I observed a weird memory growth when I set the TEST.SCALE down from 800 to 600 or 200, consuming memory 872MiB(800), 1504MiB(600), 3035Mi(200). The default config is `configs/baselines/e2e_faster_rcnn_R-50-C4_1x.yaml `...

JudyYe

Just to make sure if I have really understand the meanings of `README.md`. I am working with a single gpu and I am training on my own dataset. My dataset...

CoinCheung