-
I am using matconvnet doing human pose estimation.
1. I am using the latest code.
1. My machine is Alienware Aurora R6. CPU:i7-7700k, 32GB DDR4 2400MHz, GPU: gtx 1080, cuda 8.0, cudnn 5.1.
1. Compi…
-
## 🚀 Feature
A default optimization that LitServe can provide users is to map the `decode_request` function in case of dynamic batching using a ThreadPool. This can be useful for cases like ima…
-
Thank you so much for your contributions.
I'm trying to train model to detect architectural objects and none of the models i train seems to detect long and thin object (as illustrated in the attach…
-
I tried using wide_resnet_imagenet64_1000, but found that it is giving zero accuracy. So, wanted to double check if this usage is correct. Here I am evaluating its natural accuracy on: Imagenet64_val…
-
Is it possible to have ResNet-50 for this approach?
Arsey updated
7 years ago
-
Hi,
I am planning to use different backbones (resnext-101, resnet-152) different than that you've already provided. As you said in readme, the backbone models are converted from caffe version. Coul…
-
thank you for your greate jobs. I see you report the result with res-18 for imagenet in your paper. Do you have trained more deep layers for imagenet or some other largescale dataset? for example res…
zjupx updated
6 years ago
-
I Just want to know if this Face Recognition usses CNN, and if it is the case, what kind of architecture you used?
-
In the paper,the appearance features are extracted using ResNet-152,and the motion features are computed using a Kinetics pre-trained I3D flow network.
I really want to know how this part is p…
-
I have some trouble when i train 152-layer resnet.
1. Sometimes core dump throw when I start training, then I use command dmesg to check out, the result is blow:
![image](https://cloud.githubusercont…