alexlee-gk

Configure IP address in Windows XP
Start
Settings
Network Connections
Local Area Connections
Properties
Internet Protocol (TCP/IP)
Properties
IP address: 10.0.0.2
Subnet mask: 255.255.255.0

alexlee-gk

Install caffe with python 3.5 and pyenv

Tested on Ubuntu 14.04.

Setting up a new python environment using pyenv

Install desired version of python 3 (e.g. 3.5.1). Make sure to use the --enable-shared flag to generate python shared libraries, which will later be linked to.

env PYTHON_CONFIGURE_OPTS="--enable-shared" pyenv install 3.5.1

alexlee-gk

#Install blender as a module with python 3.5 and pyenv

Tested on Ubuntu 14.04.

Setting up a new python environment using pyenv

Follow instructions from here.

Installing boost

Follow instructions from here.

alexlee-gk

Installing TensorFlow on Instructional Machines with GPU support

These instructions were adapted from here.

The following was tested on the hive machines (e.g. hive10.cs.berkeley.edu).

Install cuDNN and setup CUDA environment variables

Download and install cuDNN.

alexlee-gk

import numpy as np
import time
import cv2
from direct.showbase.ShowBase import ShowBase
from panda3d.core import FrameBufferProperties, WindowProperties
from panda3d.core import GraphicsPipe, GraphicsOutput
from panda3d.core import Texture
from panda3d.core import loadPrcFileData

loadPrcFileData('', 'show-frame-rate-meter true')

alexlee-gk

import numpy as np
import theano
import theano.tensor as T
import lasagne.layers as L


class LocallyConnected2DLayer(L.Conv2DLayer):
    """Similar to Conv2DLayer except that the filter weights are unshared

    This implementation computes the output tensor by iterating over the filter

alexlee-gk

This was tested on a ThinkPad P70 laptop with an Intel integrated graphics and an NVIDIA GPU:

lspci | egrep 'VGA|3D'
00:02.0 VGA compatible controller: Intel Corporation Device 191b (rev 06)
01:00.0 VGA compatible controller: NVIDIA Corporation GM204GLM [Quadro M3000M] (rev a1)

A reason to use the integrated graphics for display is if installing the NVIDIA drivers causes the display to stop working properly. In my case, Ubuntu would get stuck in a login loop after installing the NVIDIA drivers. This happened regardless if I installed the drivers from the "Additional Drivers" tab in "System Settings" or the ppa:graphics-drivers/ppa in the command-line.

alexlee-gk

import os

import numpy as np


def save_gif(gif_fname, images, fps=4):
    """
    To generate a gif from image files, first generate palette from images
    and then generate the gif from the images and the palette.
    ffmpeg -i input_%02d.jpg -vf palettegen -y palette.png

alexlee-gk

import tensorflow as tf
from tensorflow.python.util import nest


def _with_flat_batch(flat_batch_fn):
    def fn(x, *args, **kwargs):
        shape = tf.shape(x)
        flat_batch_x = tf.reshape(x, tf.concat([[-1], shape[-3:]], axis=0))
        flat_batch_r = flat_batch_fn(flat_batch_x, *args, **kwargs)
        r = nest.map_structure(lambda x: tf.reshape(x, tf.concat([shape[:-3], x.shape[1:]], axis=0)),

alexlee-gk

import numpy as np
import tensorflow as tf

from video_prediction.ops import pad2d_paddings, conv2d, deconv2d, upsample2d, upsample_conv2d, pool2d, conv_pool2d


def test_upsample_conv2d():
    sess = tf.Session()
    batch = 16
    for strides in ([2, 2], [3, 4]):