Skip to content

issues Search Results · repo:wkentaro/pytorch-fcn language:Python

Filter by

142 results
 (58 ms)

142 results

inwkentaro/pytorch-fcn (press backspace or delete to remove)

I can t change it directly.
  • Lukashsx
  • 1
  • Opened 
    on Apr 29, 2023
  • #168

I wanted to change the initialization method of the convolution from 0 to a positive-terrestrial distribution, but this led to a gradient explosion after a few iters.Why does this happen?
  • eadstry
  • Opened 
    on Oct 22, 2022
  • #167

pretrained_model = \ osp.expanduser( ~/data/models/pytorch/fcn32s_from_caffe.pth ) How does this line of code work
  • zsxzs
  • 1
  • Opened 
    on Mar 27, 2022
  • #166

Traceback (most recent call last): File demo.py , line 59, in module demo(args) File demo.py , line 45, in demo model = get_model(args.model, local_rank=args.local_rank, pretrained=True, root=args.save_folder).to(device) ...
  • Shajiu
  • Opened 
    on Nov 24, 2021
  • #165

viz = fcn.utils.visualize_segmentation(lbl_pred=lp, lbl_true=lt, img=img, n_class=n_class) in the validate function in trainer.py,i can not find the visulaize_segmentation function.could you please tell ...
question
  • liul-ing
  • 1
  • Opened 
    on Nov 2, 2021
  • #164

the code ”import fcn“ can lead the error:”no module named fcn“,what should i do?
question
  • liul-ing
  • 1
  • Opened 
    on Nov 2, 2021
  • #163

It looks like array slice, but what 31 means? And h[:, :, 5:5 + upscore2.size()[2], 5:5 + upscore2.size()[3]] also confuses me
  • lyw615
  • 6
  • Opened 
    on Jun 10, 2021
  • #161

I tried to open http://drive.google.com/uc?id=0B9P1L--7Wd2vVGE3TkRMbWlNRms but get 404 for result
  • BlackDriver
  • 4
  • Opened 
    on May 30, 2021
  • #160

I was running the code on google colab. I downloaded the dataset by !sh ./download_dataset.sh . ##Use the command !python ./train_fcn32s.py -g 0 . And I got the problem. Here is the error sign. fatal: ...
  • dmndxld
  • Opened 
    on Apr 25, 2021
  • #159

I wonder why the padding of first conv layer in FCN32s is 100? FCN32s( (conv1_1): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(100, 100)) I am a newcomer in ML.Can you give me some answer? ...
  • msy1412
  • 3
  • Opened 
    on Nov 29, 2020
  • #157
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue search results · GitHub