Closed MBaltz closed 2 years ago
Hi MBaltz. One of the pretrained models can be find here: https://drive.google.com/drive/folders/11KnYVFE59l9_0Q045zmnU24agtjynFbK?usp=sharing
This is implemented on 4 GPUs. Please use the following code in the solve.py --> test() function to load the model.
self.TEDNet = TED_Net(img_size=64,tokens_type='performer', embed_dim=64, depth=1, num_heads=8, kernel=8, stride=4, mlp_ratio=2., token_dim=64) if (self.multi_gpu) and (torch.cuda.device_count() > 1): self.TEDNet = nn.DataParallel(self.TEDNet) ## data parallel self.TEDNet.to(self.device) self.load_model(self.test_iters)
Okay @wdayang !
I already request the google drive file acess. I'll try right now and return here to say if all right.
Thank you so much for this.
Ok, if you have any questions, please let me know.
Sorry Mateus,
I accidentally closed your issue on the github. you may email me if there is other problems.
Best, Dayang
On Fri, Feb 18, 2022 at 10:15 AM Mateus Baltazar @.***> wrote:
Okay @wdayang https://github.com/wdayang !
I already request the google drive file acess. I'll try right now and return here to say if all right.
Thank you so much for this.
— Reply to this email directly, view it on GitHub https://github.com/wdayang/CTformer/issues/2#issuecomment-1044684744, or unsubscribe https://github.com/notifications/unsubscribe-auth/AFQCHCQYL42AFEGDEIBPAALU3ZPCPANCNFSM5OVVSLLQ . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.
You are receiving this because you were mentioned.Message ID: @.***>
Hello @wdayang.
The shared weights were loaded with success! For this, I used this modification: https://github.com/knazeri/edge-connect/issues/121#issuecomment-1048382609
Thank you so much!
Please, can you share with us the trained weights used in paper (4000 epochs or others)?
Thanks! Congratulations for your work!