Efficient-3DCNNs
Efficient-3DCNNs copied to clipboard
okankop
PyTorch Implementation of "Resource Efficient 3D Convolutional Neural Networks", codes and pretrained models.
I tried to convert the 3DCNN model to onnx,but the inference results by onnx and pytorch are different.I tried the backbone of resnet18 and mobilenet.Did anybody meet the same problem?...
Hi there, thanks for the work. We are trying to reproduce the experiments, however, both training and validation top1 accuracy were closed to 0. We followed the configuration in another...
Hi, I downloaded you repository and the Jester dataset, then I followed the instructions contained in the "README.md" file to preprocess the dataset in order to obtain the files required...
Hi, The pretrained Jester models give around 50% acc at best. I tried MobileNetV2, MobileNet, and ShuffleNet. Any tips? Thanks
Hi! Thank you for your code. I run this. ``` python utils/ucf101_json.py annotation_dir_path ``` then caught this error. ``` 'DataFrame' object has no attribute 'ix' ``` At pandas >= 0.2.0,...
Hi, thanks for sharing the project codebase! 😊 I'm having issues reproducing any sort of results on Kinetics using your [pretrained models](https://drive.google.com/open?id=1eggpkmy_zjb62Xra6kQviLa67vzP_FR8). So far, I have: - Downloaded Kinetics600 using...
Hi! There are some implementation details on training 3DCNNs on UCF101 in your paper[1], one of which is "While dropout ratio is kept at 0.2 for Kinetics600 and Jester, it...
Here is the code, modified from https://github.com/d-li14/mobilenetv3.pytorch/blob/master/mobilenetv3.py 's 2D MobileNetV3: ```python import math import torch import torch.nn as nn import torch.nn.functional as F from torch.autograd import Variable def _make_divisible(v, divisor,...
First of all, awesome repository! I wanted to ask if you were using mean and std calculated on the whole jester dataset for normalizing images during training on the jester...
Hi, thank you for your code. utils.py is easy to cause conflict when from utils import *. I don't know if you have encountered the same problem, you can change...
