lixiang

check failed: target_blobs.size() == source_layer.blobs_size() (1 vs. 0). Incompatible number of blobs for layer conv1_1/conv

4

i'm using pva-faster-rcnn on windows+cuda8.0. I'm trying to training my own data (1 object class and background) with the following code: python tools/train_net.py --gpu 0 --solver models/pvanet/example_train/solver.prototxt --weights models/pvanet/pva9.1/PVA9.1_ImgNet_COCO_VOC0712.caffemodel --iters...

how can i run it on windows?

1

There's some trouble with my gpu, it cannot get through on ubuntu. Is there any one who has run the pvanet on windows?

AssertionError: assert len(top) == len(self._name_to_top_map)

7

i have successfully trained the net my own data using end2end training. However, when training using alternative training, i meet the same error "assert len(top) == len(self._name_to_top_map) AssertionError". I have...

got infinite loss when training modelnet40 dataset

2

Hello Christopher, I'm trying to evaluate your model on the synthetic ModelNet40 dataset. I wrote my own dataloader and trained your model with the default settings. But after a few...

Hi, @deep-unlearn , can you provide a copy of the nDSM data? I didn't find this dataset in the contest website.

Does the faster rcnn method support multi-scale training and testing? The training scale parameter in configure file is a matrix, does it means it supports multi -scale training? But the...

experience about detect small object

1

is there anyone who can share his or her experience about parameter setting when detecting small object using Faster RCNN?

cannot run worldcount

3

i follow the instructions and successful startup the hadoop using ./start_hadoop.sh. But when i run the wordcount example, i got this messages, and it just stop there: root@hadoop-master:~# ./run-wordcount.sh mkdir:...