Peter Lorenz

HTTPError: HTTP Error 503: Service Unavailable

1

deeplearning-models/pytorch_ipynb/cnn/cnn-resnet50-mnist-dataparallel.ipynb ``` Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to data/MNIST/raw/train-images-idx3-ubyte.gz 0it [00:00, ?it/s] --------------------------------------------------------------------------- HTTPError Traceback (most recent call last) in 5 # Note transforms.ToTensor() scales input images 6 # to 0-1 range ---->...

``` /home/user/.conda/envs/bm/lib/python3.7/site-packages/torch/jit/_trace.py:152: UserWarning: The .grad attribute of a Tensor that is not a leaf Tensor is being accessed. Its .grad attribute won't be populated during autograd.backward(). If you indeed want...

Replacing in train.py the line: ```loss_function = nn.CrossEntropyLoss()``` with ``` cw = torch.tensor([0.11850941, 0.14937713, 0.11032023, 0.62179323], dtype=torch.float32).cuda() # class weights for 1, 2, 3, 4 loss_function = nn.CrossEntropyLoss(ignore_index=255, weight=cw, reduction='mean')...

FALCONN KNN alternative to save as pickle?

1

Does anybody know a FALCONN KNN alternative, which can be saved as pickle?

4 classes model; targeted attacks are different

2

Follow up from https://github.com/fra31/auto-attack/issues/76 Since I have a model trained in only 4 classes I adapted the number of targets `t`. I changed this block: https://github.com/fra31/auto-attack/blob/6482e4d6fbeeb51ae9585c41b16d50d14576aadc/autoattack/autoattack.py#L265 to ``` elif version...

setting up with docker [still not working]

1

My setup: Carla ``` #download docker image (e.g. version 0.9.6) docker pull carlasim/carla:0.9.6 #extract the Carla Python API from the image cd ~ mkdir carla-python docker run --rm --entrypoint tar...

According to this Video: https://www.youtube.com/watch?v=Z7PLkcY9Mtk it is possible to run Openplanner with Carla. After the debugging the GUI of Autoware 12, because I use Ubuntu 18, I tried to launch...

Hi @fabianoboril @fpasch, the bridge is almost working with the carla 0.9.7.4 (https://github.com/carla-simulator/carla/releases). But the autonomous vehicle loses the localization all the time. I also had this problem with 0.9.6...

project for pytorch.

2

Hello, is there any good code base in pytorch available?

### What's the feature? I want to have a different initialization variable. ### Any other context? The variable noise https://github.com/ZhendongWang6/DIRE/blob/864006958b31dae4f7333f7fd2d683002b378367/guided-diffusion/compute_dire.py#L100 is initialized for the forward process... I would need something...