Jack

Installation failed, on Python 3.6, Ubuntu 16.04 x64

4

### Evironment: I use Miniconda on Ubuntu 16.04 x64. ``` Python 3.6.2 |Continuum Analytics, Inc.| (default, Jul 20 2017, 13:51:32) [GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux Type "help",...

PyTorch: The kernel appears to have died. It will restart automatically.

34

System: Ubuntu 16.04 LTS 64-bit As the picture shows, after `import torch`, the kernel died and restarting.  Python version ``` Python 2.7.12 (default, Nov 19 2016, 06:48:10) [GCC 5.4.0...

Is there a data preprocessing script for the rope dataset?

1

Firstly, thank you for your great work! The format of provided dataset [google drive link](https://drive.google.com/file/d/1pnX8gGqs5EQVjGy4Z6FZ5oZ9noDHlC_8/view) is not completely fit to the [training code / dataloader](https://github.com/pathak22/zeroshot-imitation/blob/master/train.py). For example, there is no...

ValueError: Variable net_-1/basic_lstm_cell/weights does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

2

Environment: Python 3.5.2 TensorFlow 1.2.1 ``` Traceback (most recent call last): File "a3c.py", line 70, in device = device) File "/home/jack/Applications/async_deep_reinforce/a3c_training_thread.py", line 51, in __init__ self.gradients ) File "/home/jack/Applications/async_deep_reinforce/rmsprop_applier.py", line...

modprobe: ERROR: could not insert 'fglrx': Function not implemented

3

After `pip install gym[atari]`, `pip install scipy` and change `PongDeterministic-v3` to `PongDeterministic-v4`, [A3C-PyTorch](https://github.com/onlytailei/A3C-PyTorch) works well on my computer. But when I run `./train_lstm.sh` on the server through `ssh -X`, the...

Pointcloud Projection Into Images

2

Hi, RobotCar Team, Firstly, thank you for your great dataset! I followed the https://robotcar-dataset.robots.ox.ac.uk/documentation/#pointcloud-projection-into-images to project pointcloud into images using the Python API provided by the SDK. However, the result...

ModuleNotFoundError: No module named 'data'

2

First, thank you for your great work! It seems that `data.py` is missing. When I run `python train_celeba_128.py`, the following error reported: 

It seems there is a bug of test process. Although the error is `out of memory`, I think there are other reasons. Because I have also implemented a naive test...