-
Hi, package developers,
I encountered an issue with the import robustness. dataset and I think the potential problem occurs in the vgg.py file under imagenet models.
potential changes from
…
-
Hi,
I would like to train the model on a different dataset. But I am not able to get the pre-trained weights for vgg-19 parameters. The link says that owner has deleted the weights. Can you please h…
-
I use RepVGG A2 as Backbone segmentation. After converting to engine TensorRT, float 16 keep the mIOU as the pytorch model, but when I convert to int8 TensorRT, mIOU drop ~5%. Did you try it yet?
-
# Description
tl;dr: The pre-trained SSD checkpoint has a huge loss while training on the **VOC2007 train + val** dataset and it doesn't seem to be anywhere near convergence.
I was trying to use…
-
When I change traditional conv with deformable conv, the training speed is 10✖ times lower than before with a vgg backbone. my pytorch version is v1.1 and my cuda is v10.1. Anyone knows how to improve…
-
Hello, I admire you for doing such an excellent job. I would like to ask how you designed this CNN architecture to achieve such good performance in the end? How did you determine the structure of the …
-
大家好,请问如何利用一个已有的网络,比如VGG,训练一张图片,使得它在狗这个类别上的概率最大呢
-
hello,I just reproduced your code. Using UAP existing under perturbations folder and ILSVRC2012 for verification, I found that the fooling rate was much higher than that in the paper. For example, UAP…
-
Running an updated example using gradient sharing and VGG 16 from zoo. With a batch size of 16, zoo model uses 10GB of memory from defaults. This happens when isolated from ParallelWrapper. Have also …
-
Hi! I was wondering if there is any possibility in Caffe to compress a neural network.
In this paper [Deep compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman…