Comments (4)
Sure, @MENG2010 please post the logs here.
from athena.
INFO: compile model using customized metrics.
Traceback (most recent call last):
File "scripts.py", line 298, in <module>
tf.app.run()
File "/opt/DL/tensorflow/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "scripts.py", line 280, in main
generate_adversarial_examples(DATA.mnist, ATTACK.FGSM)
File "scripts.py", line 124, in generate_adversarial_examples
X_adv, _ = get_adversarial_examples(model_name, method, X, Y, eps=eps)
File "/home/ymeng/advML/attacks/attacker.py", line 30, in get_adversarial_examples
X_adv, Y = whitebox.generate(model_name, X, Y, attack_method, attack_params)
File "/home/ymeng/advML/attacks/whitebox.py", line 170, in generate
metrics=['accuracy', adv_accuracy_metric]
File "/opt/DL/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/checkpointable/base.py", line 474, in _method_wrapper
method(self, *args, **kwargs)
File "/opt/DL/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 648, in compile
sample_weights=self.sample_weights)
File "/opt/DL/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 313, in _handle_metrics
output, output_mask))
File "/opt/DL/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 270, in _handle_per_output_metrics
y_true, y_pred, weights=weights, mask=mask)
File "/opt/DL/tensorflow/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_utils.py", line 598, in weighted
score_array = fn(y_true, y_pred)
File "/home/ymeng/advML/attacks/whitebox.py", line 228, in adv_acc
x_adv = attacker.generate(model.input, **attack_params)
File "/opt/anaconda3/lib/python3.6/site-packages/cleverhans/attacks.py", line 342, in generate
labels, _nb_classes = self.get_or_guess_labels(x, kwargs)
File "/opt/anaconda3/lib/python3.6/site-packages/cleverhans/attacks.py", line 281, in get_or_guess_labels
preds = self.model.get_probs(x)
File "/opt/anaconda3/lib/python3.6/site-packages/cleverhans/utils_keras.py", line 179, in get_probs
return self.get_layer(x, name)
File "/opt/anaconda3/lib/python3.6/site-packages/cleverhans/utils_keras.py", line 227, in get_layer
output = self.fprop(x)
File "/opt/anaconda3/lib/python3.6/site-packages/cleverhans/utils_keras.py", line 203, in fprop
self.keras_model = KerasModel(new_input, out_layers)
File "/opt/anaconda3/lib/python3.6/site-packages/Keras-2.2.4-py3.6.egg/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/opt/anaconda3/lib/python3.6/site-packages/Keras-2.2.4-py3.6.egg/keras/engine/network.py", line 94, in __init__
self._init_graph_network(*args, **kwargs)
File "/opt/anaconda3/lib/python3.6/site-packages/Keras-2.2.4-py3.6.egg/keras/engine/network.py", line 253, in _init_graph_network
input_shapes=[x._keras_shape for x in self.inputs],
File "/opt/anaconda3/lib/python3.6/site-packages/Keras-2.2.4-py3.6.egg/keras/engine/network.py", line 253, in <listcomp>
input_shapes=[x._keras_shape for x in self.inputs],
AttributeError: 'Tensor' object has no attribute '_keras_shape'
from athena.
some said this AttributeError was caused by mixed usage of keras.model with tensorflow.keras.model. However, we only use tensorflow.keras.model package in our codes.
https://stackoverflow.com/questions/54614299/tensor-object-has-no-attribute-keras-shape
from athena.
Should be the same issue one google cloud platform.
#9
from athena.
Related Issues (20)
- Test if the current defenses does not reply on a specifc AE type HOT 2
- make current defense approaches (ensemble models) to not depend on a specific AE type HOT 1
- Accuracy of some transform models are lower than that of clean model HOT 1
- manage the information with logging
- use FLAG to manage configurations
- exceptions were thrown when applying some sort of transformations HOT 1
- poisson-noise transformation model crashes when predicting the AE, jsma (theta-10, gamma-30) HOT 2
- Readme for the project showing the end top end workflow HOT 1
- Visualizing label separateability using t-sne HOT 1
- Investigate how adv attacks change the class activation mapping (CAM) HOT 1
- Tune and fix bugs for new transformations HOT 7
- Organize the defense in a folder HOT 1
- SC computing cluster: deploy a docker container that could access a GPU node
- End-to-end demo for our defense approach HOT 1
- Support MIM attack HOT 1
- Evaluate White-box Threat Model HOT 1
- Evaluate Grey-box Threat Model HOT 1
- refactor HOT 1
- Normalized l2-dissimilarity HOT 4
- reset function in src/evaluation/eval_whitebox.py HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from athena.