BarclayII

'''
Original implementation
https://github.com/clab/dynet_tutorial_examples/blob/master/tutorial_parser.ipynb

The code structure and variable names are similar for better reference.

Not for serious business, just for some comparison between PyTorch and DyNet
(and I still prefer PyTorch)
'''
import torch as T

BarclayII

import tensorflow as TF
import modeltf as model

import numpy as NP
import numpy.random as RNG

import h5py

import argparse

BarclayII

#!/usr/bin/env python

"""
Code to load an expert policy and generate roll-out data for behavioral cloning.
Example usage:
    python run_expert.py experts/Humanoid-v1.pkl Humanoid-v1 --render \
            --num_rollouts 20

Author of this script and included expert policies: Jonathan Ho ([email protected])
"""

BarclayII

# Modified from example/autograd/{data,dcgan}.py to make it standalone.
import argparse
import mxnet as mx
from mxnet import nn
from mxnet.contrib import autograd
import numpy as np
import matplotlib.pyplot as PL
import time
import os

BarclayII

import argparse
import mxnet as mx
from mxnet import nn
from mxnet.contrib import autograd
import numpy as np
import time
import os

ngpu = 1
nz = 100

BarclayII

import torch as T
import numpy as NP

### Norm of vector difference

# Checker
def normdiff_assert(X, Y, normdiff):
    norm = normdiff(X, Y)
    for i in range(X.size()[2]):

BarclayII

import torch as T
import numpy as np
x = T.autograd.Variable(T.randn(5, 8), requires_grad=True)
p = T.nn.functional.softmax(x)
y = p.multinomial()
y.reinforce(T.ones(y.size()))
y.backward()
d = x.grad.data.clone().numpy()
x.grad.data.zero_()
logp = T.nn.functional.log_softmax(x)

BarclayII

# References:
# https://arxiv.org/pdf/1405.5869.pdf
# https://arxiv.org/abs/1507.05910

import numpy as np
from scipy.spatial.distance import cosine

# Rescaling and appending new components to "normalize" data vectors
X = np.random.randn(10000, 100)
Xn = np.sqrt((X ** 2).sum(1))

BarclayII

#include <unordered_map>
#include <map>
#include <vector>
#include <iostream>
#include <utility>
#include <cstdint>
#include <ctime>
#include <cstdlib>

using std::uint64_t;

BarclayII

import torch
import time

N = 10000
D = 50
E = 500000
T = 10

t_gather = 0
t_scatter = 0