-
I use a trained pytorch model-resnet18 in foolbox. The model is trained to classify only 2 classes, and first loaded in python. But when I use it to make adversarial examples, it reported assertion Er…
-
-
```
import foolbox
import keras
import numpy as np
from keras.applications.resnet50 import ResNet50
# instantiate model
keras.backend.set_learning_phase(0)
kmodel = ResNet50(weights='imagenet…
pGit1 updated
6 years ago
-
The `TargetClassProbability` criterion seems to behave stragely in some cases: for example, with `FashionMNIST`:
```
fmodel = foolbox.models.PyTorchModel(model, (0, 1), num_classes=10, channel_axi…
-
I 'm running the following model:
```
input1 = Input(shape=(length_timestamps,))
x1 = Embedding(size_icd, int(6 * size_icd ** (1. / 3)), input_length=length_timestamps)(input1)
input2 = Input(…
-
Pytorch using image in CxWxH way which is consistent with TF makes preprocess not work
-
Hi,
When attempting to run the [MNIST example](https://github.com/marcoancona/DeepExplain/blob/master/examples/mint_cnn_keras.ipynb) for DeepLift, I get the following error:
```
InvalidArgumentEr…
-
Hello!
Although I know avc-test-model-against-attack is not published yet, after reading the code, the problem still seems strange to me: When I run
```
./avc-test-model-against-attack --model_dire…
-
I am using a standard VGG16 and and trying to generate adversarial images using different attacks, however i am always greeted by this error : ValueError: Cannot feed value of shape (1, 1) for Tensor …
-
Swift is a very popular and expressive language with a large community of pro developers.