youngxiao13/fewshotviewpoint

(ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"

fewshotviewpoint's Issues

Demo

Hi,

Is it possible to run the code as a demo on my own images? Can you please provide a guide on how to do this?

Thank you!

HTTP 404 NOT FOUND for url

I got error for the following links and I have added the updated links-

1. HTTP 404 NOT FOUND for url https://conda.anaconda.org/pytorch/linux-64/pytorch-1.0.1-py3.6_cuda8.0.61_cudnn7.1.2_2.tar.bz2

https://conda.anaconda.org/pytorch/noarch/torchvision-cpu-0.2.2-py_3.tar.bz2

2. Unable to solve

HTTP 404 NOT FOUND for url <https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/linux-64/pytorch-1.0.1-py3.6_cuda8.0.61_cudnn7.1.2_2.tar.bz2>

Can't download the point clouds for this dataset

download_object3d.sh #22

wget --header 'Host: uc23d47b3615cc6557d59b6a3ae5.dl.dropboxusercontent.com' --user-agent 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:66.0) Gecko/20100101 Firefox/66.0' --header 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8' --header 'Accept-Language: en-US,en;q=0.5' --referer 'https://www.dropbox.com/' --header 'Upgrade-Insecure-Requests: 1' 'https://uc23d47b3615cc6557d59b6a3ae5.dl.dropboxusercontent.com/cd/0/get/A8GKqmoG-OuJ_z0eMpz12RGIfC8UmGoK1_gkgL3tskQz4WydJr50I_SqcdywnzBoca01TpfUAf6rCXlifu6ss6MqKD2XjA1ooD90Ge9qeQNtTo1Nl-q7kXWrCHkKy0lenLM/file#' --output-document 'ObjectNet3DPointclouds.zip'

I request you to offer Google drive links of point clouds data of ObjectNet3D and Pascal3D dataset
thanks a lot

RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

Hi @YoungXIAO13

I have been trying to run the demo script and I am getting the following error. Can you help out here? I am somewhat inexperienced with pytorch.

Traceback (most recent call last):
  File "demo.py", line 79, in <module>
    out = model(im, None, mean_class_data=cls_data)
  File "/home/samagra14/miniconda3/envs/FSviewpoint/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/samagra14/6d_pose/FewShotViewpoint/auxiliary/model.py", line 103, in forward
    img_feature = self.img_encoder(im)  # B*C
  File "/home/samagra14/miniconda3/envs/FSviewpoint/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "./auxiliary/resnet.py", line 137, in forward
    x = self.conv1(x)
  File "/home/samagra14/miniconda3/envs/FSviewpoint/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/samagra14/miniconda3/envs/FSviewpoint/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 320, in forward
    self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

Thanks

wget