pytorch-faster-rcnn issues

KeyError: 'resnet.bn1.num_batches_tracked'

2

I got an error message below when I executed the demo with the trained model using res101 on VOC dataset : Traceback (most recent call last): File "./tools/demo.py", line 164,...

AI-MD

Slower than tf-faster-rcnn

2

This code is taking more time to train than the [tf-faster-rcnn](https://github.com/endernewton/tf-faster-rcnn). When I am running at 1800 scale this code is taking 2.9 sec /iter as compared to 1.7sec/iter in...

rnsandeep

Check prediction image in tensorboard

Hi, I can see only the GT images on tensorboard during training, but I would like to also see the inference, as shown in the Readme. How can I enable...

mees

memory error when train voc dataset

2

``` Loading initial model weights from data/imagenet_weights/res101.pth Loaded. Traceback (most recent call last): File "./tools/trainval_net.py", line 192, in sw.train_model(iters_sum) File "/home/nieqinqin/liuxiaoyu/SSM-Pytorch/tools/../lib/model/train_val.py", line 295, in train_model self.net.train_step_with_summary(blobs, self.optimizer) File "/home/nieqinqin/liuxiaoyu/SSM-Pytorch/tools/../lib/nets/network.py", line...

ShawnLiu1011

Can this model be trained on multiple GPU?

liuboss1992

ImportError: ../_roi_pooling.so: undefined symbol: __cudaPopCallConfiguration

2

Hi, Thank you for your great work. I have some error with roi_pooling layer (also nms and roi_align). `Traceback (most recent call last): File "./tools/test_net.py", line 18, in from nets.vgg16...

hesedjds