Search results

A question about the back propagation algorithm in crown

Status: Open.

#6 In huanzhang12/RecurJac-and-CROWN;

· ydingWiley opened on Nov 7, 2022

Does this repository support robust boundary calculations of CROWN-IBP type?

Status: Open.

#5 In huanzhang12/RecurJac-and-CROWN;

· nbdyn opened on Oct 26, 2022

What's the different between crown_adaptive_bound and crown_general_bound

Status: Open.

#4 In huanzhang12/RecurJac-and-CROWN;

· nbdyn opened on Oct 25, 2022

Local Lipschitz constant on customized Pytorch network

Status: Open.

#3 In huanzhang12/RecurJac-and-CROWN;

· yifei-liu-stat opened on Dec 6, 2021

# python3 main.py --task robustness --numimage 10 --targettype random --norm i --modelfile ../models/mnist_3layer_relu_1024_adv_retrain --layerbndalg crown-adaptive --jacbndalg recurjac --eps 0.2 Loading model ../models/mnist_3layer_relu_1024_adv_retrain 2021-07-26 08:37:45.812888: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: SSE4.1 SSE4.2 AVX AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. WARNING:tensorflow:No training configuration found in the save file, so the model was *not* compiled. Compile it manually. Model imported using keras Traceback (most recent call last): File "/home/RecurJac-and-CROWN-master/main.py", line 145, in <module> if input_dim[2] == 28 or input_dim[2] == "28": IndexError: list index out of range

Status: Open.

#2 In huanzhang12/RecurJac-and-CROWN;

· aspnetcs opened on Jul 26, 2021

Certifying robustness on custom network

Status: Open.

#1 In huanzhang12/RecurJac-and-CROWN;

· lhfowl opened on Apr 24, 2019