-
[timm](https://github.com/rwightman/pytorch-image-models) is **the largest** library of image models. Not only that, it also has a unified and very simple to use interface, that stays the same across …
-
Hi, where does "from inplace_abn import InPlaceABN" come from ?
-
I want to speed up the tresnet_m go a step further, if I modify the bottlebneck strcture"[3,4,11,3]" to "[3,4,8,3]"，the network can work too. Do you compare the modified "[3,4,8,3]" or "[3,4,6,3]" to…
-
**Describe the bug**
I tried using the distributed train to train my custom dataset using TResnet but given the error of installing tresnet. I already install inplace-ABN via pip before
**To Repro…
-
Hi, I'm impressed by your great work! I'm wondering would it be possible for you to release the model checkpoints after you trained from the pre-trained ImageNet-21k-P weights by your semantic KD on I…
-
Hi,
Thank you for your great work! I am currently trying to run your code with a larger batch size to better parallelize the code. Could you provide some hints on how to adjust the learning rate w…
-
Hello,
Very nice work. I am highly inspired by it and working on training from the scratch. I have a question regarding the default pre-trained weights which you have used to initialize the trainin…
-
https://github.com/Alibaba-MIIL/ImageNet21K/blob/00ef9989825bbcb8dedc91eac18638c129eb5ad8/src_files/models/utils/factory.py#L54
Why do we need to load pretrained ImageNet-1K model if we are going t…
-
Hi @mrT23, I don't see the module [SelectAdaptivePool2d](https://github.com/Alibaba-MIIL/TResNet/blob/d95cffad2b9088d0f82852e30b35b1ae2469a6a0/src/models/tresnet_v2/tresnet_v2.py#L10) in tresnet_v2.py…
ngun7 updated
3 years ago
-
@mrT23 Dear sir, when I use the pretrained imagenet21k model and set the lr = 0.01or 0.1 rather than default lr value 0.0003,the Accurancy is very low, such as 0.17% util train dozens of epochs.
if …