matpalm

#include <array>
#include <cmath>
#include <cstdint>

#include "daisy_patch.h"
#include "daisysp.h"

using namespace daisy;

namespace

matpalm

#include <array>
#include <cstdint>

#include "daisy_patch.h"
#include "daisysp.h"

using namespace daisy;

namespace
{

matpalm

#!/usr/bin/env python                                                                                                                     
# gpu_stat.py [DELAY [COUNT]]                                                                                                             
# dump some gpu stats as a line of json                                                                                                   
# {"util":{"PCIe":"0", "memory":"11", "video":"0", "graphics":"13"}, "used_mem":"161"}                                                    

import json, socket, subprocess, sys, time
try:
    delay = int(sys.argv[1])
except:
    delay = 1

matpalm

import numpy as np

def slerp(p0, p1, n):
    # https://en.wikipedia.org/wiki/Slerp
    norm = np.linalg.norm(p0) * np.linalg.norm(p1)
    dot = np.sum(p0 * p1 / norm)
    theta_0 = np.arccos(dot)
    sin_theta_0 = np.sin(theta_0)
    interp = []
    for t in np.linspace(0.0, 1.0, n):

matpalm

#!/usr/bin/env python                                                                                                                                                                     
# gpu_stat.py [DELAY [COUNT]]                                                                                                                                                             
# dump gpu stats as a line of json                                                                                                                                                        
# {"time": 1474168378.146957, "pci_tx": 146000, "pci_rx": 1508000,                                                                                                                        
#     "gpu_util": 42, "mem_util": 24, "mem_used": 11710,                                                                                                                                  
#     "temp": 76, "fan_speed": 44, "power": 65 }                                         

matpalm

#!/usr/bin/env python3

from PIL import Image
import numpy as np
import tensorflow as tf
import tensorflow_hub as hub

# smooth values from point a to point b.
STEPS = 100
pt_a = np.random.normal(size=(512))

matpalm

def triplet_loss(anchor_embeddings,
                 positive_embeddings,
                 negative_embeddings,
                 margin=0.0):
    dist_a_p = tf.norm(anchor_embeddings - positive_embeddings, axis=1)  # (B)                            
    dist_a_n = tf.norm(anchor_embeddings - negative_embeddings, axis=1)  # (B)                            
    constraint = dist_a_p - dist_a_n + margin                            # (B)                            
    per_element_hinge_loss = tf.maximum(0.0, constraint)                 # (B)                            
    return tf.reduce_mean(per_element_hinge_loss)

matpalm

class EmbeddingModel(keras.Model):
  
  def train_step(self, data):      
    anchors, positives = data     
    print("a,p", anchors.shape, positives.shape) 

    with tf.GradientTape() as tape:
      # Run both anchors and positives through model.
      anchor_embeddings = self(anchors, training=True)
      positive_embeddings = self(positives, training=True)

matpalm

import numpy as np

def rnd(*args):
    return np.random.random(args)

matpalm

#!/usr/bin/env python3

import argparse
import model as m
from tensorflow.keras.callbacks import *
import data as d
import tensorflow as tf
import os
from lr_finder import LearningRateFinder