-
你好我在使用你们提供的被攻击模型和我自己使用celeba64.py训练出来的模型(测试精度为93.298）作为lommagmi.py的被攻击模型时。攻击效果top1为0.3-0.4之间、top5在0.5左右.与论文《Re-thinking Model Inversion Attacks Against Deep Neural Networks》展现的实验结果相差比较大。我想了解一下产生这样的结果是…
-
I'm implementing the API on a website. I made a code that loads the model I trained and predicts on some images, but every time I load the model, the model start downloading the encoder weights. This …
-
Hi,
I'm interested in:
https://huggingface.co/timm/tf_efficientnet_b7.ns_jft_in1k
The efficientnet model is available in keras, but I'm interested in the advanced pretrained weights used here.
…
-
Do you have anything in the README on how to apply these models to new data? I understand most of this is set up to reproduce the analysis, but I wanted to know if you have a script that takes a mode…
-
**Is your feature request related to a problem? Please describe.**
Researchers often need to experiment with various CNN architectures to improve face recognition performance. Currently, the system l…
-
**Describe the bug**
Since the torch version was updated, the provided pretrained weights no longer match the efficientnet model and can't be loaded in.
**To Reproduce**
```python
from torchsig.…
-
- decision metrics
-
Congrats on this great work and the recent publication in npj PO.
We tried to follow the code in the get_slide_tls.py and had the issue loading
FileNotFoundError: [Errno 2] No such file or dire…
-
hey @UppuluriKalyani
I am Darsh Agrawal , a fellow contributor and I would like to contribute by using Transfer learning and create a model to help various agencies label captured terrain images li…
-
```
PS C:\Users\akimio\Documents\Work\Kaggle-Steel-Defect-Detection> pip install git+https://github.com/qubvel/segmentation_models.pytorch
Collecting git+https://github.com/qubvel/segmentation_model…