-
Hi,
Congrat to this impressive work.
I have a question relating to the image feature map. In the paper, you mentioned that you used ResNet34 pretrained on ImageNet as the image encoder. Could yo…
-
-
python 3dtrain.py --model pretrain_data/resnext-101-kinetics.pth --mode score --model_depth 101 --structure ResNeXt101 --batch_size 32 --model_name resnext --resnet_shortcut B --cropCsize 256 224 192 …
-
======================================================================
ERROR: test_resnet (__main__.TestResnetFp32)
----------------------------------------------------------------------
Traceback …
-
## 🐛 Bug
I tried to obtain a deeplabv3_resnet34 version based on the code that you are using for getting the resnet50 and resnet101 version
## To Reproduce
```
def deeplabv3_resnet34(pretrai…
-
### Describe the bug
Hello,
When initializing a new project, I got the error below.
I tried to upgrade: ipython and jupyter-lab, but the issue still persist.
it seems imcompatibility issues betw…
-
## About op-level-test of q-implant.
We want to check if we can proceed with q-implant on the operator used in the frequently used MobileNet, ResNet, and Inception models.
We converted the model…
-
This repo uses fb.resnet.torch for ImageNet experiments. However the performance of ResNet-50 in fb.resnet.torch is 24.01: https://github.com/facebook/fb.resnet.torch. The performance of ResNet-50 bas…
-
The CK-Caffe repository contains several duplicate files:
```
$ find $CK_REPOS/ck-caffe -name *binaryproto -exec ls -la {} \;
-rw-r--r-- 1 anton dvdt 602126 Apr 7 19:09 /home/anton/CK/ck-caffe/pac…
-
from your paper, you get top-1 accuracy 60.1% on resnet-34, but i get 57.9%.
i use your pre-train model.
the result is video accuracy.
what's the problem?
i can't download some of kinetics datas…
lee2h updated
5 years ago