-
-
Could you provide the ImageNet pretrained weights for TResNet V2?
Thank you for your attention
-
there occurs an error in the tresnet.py file. result = self.forward(*input, **kwargs)
RuntimeError: Some elements marked as dirty during the forward method were not returned as output. The inputs tha…
-
Hello, I tried to reproduce the result on COCO, I implemented my own framework and most of my files are the same as you, I only write my new train.py.
As is introduced in your paper, I have implement…
-
Hi @mrT23, I would like to run inference on Stanford cars data using pre-trained TresNet weights that achieved 96% but the weights at [Model_zoo](https://github.com/Alibaba-MIIL/TResNet/blob/master/MO…
ngun7 updated
3 years ago
-
-
Thank you very much for your work.
I trained the ASL model using one gpu sucessfully. But when I trained it using multiple GPUs. Error occurred.
So Is it possible to train ASL using multiple GPU?
-
Hi @mrT23
I am looking at the pretrained model you provided. I notice that the pretrained Tresnet-L for COCO and OpenImage have different binary size. Though COCO has fewer categories than OpenIma…
-
Thanks for the inspiring implementation :)
I'm having trouble to reproduce the results on MSCOCO with tresnet_m as backbone, 224 as input.
I have varied lr (1e-4 and 2e-4), batch_size (128 and 64)…
-
I've noticed more and more `timm` backbones being added here, which is great, but a lot of the effort is currently duplicating some features of `timm`, ie tracking channel numbers, modifying the netwo…