gidim

{
  "embeddings": [
    {
      "tensorName": "Word2Vec 10K",
      "tensorShape": [10000, 200],
      "tensorPath": "https://staging.comet.ml/api/asset/download?experimentKey=fa93606a42a942fe8ed6cafb6dacbdfc&assetId=7c6150fe13ff4682b075e3dfdf6dc33f&isCompressed=false",
      "metadataPath": "https://staging.comet.ml/api/asset/download?experimentKey=fa93606a42a942fe8ed6cafb6dacbdfc&assetId=833915c9ad624f9cad2e1a8724778443&isCompressed=false"
    }
  ],
  "modelCheckpointPath": "Demo datasets"

gidim

import json
import logging
import time
from collections import defaultdict

import os

from multiprocessing import Lock
from watchdog.observers import Observer
from watchdog.events import FileSystemEventHandler, LoggingEventHandler

gidim

{"metrics":[{"name":"acc","xSteps":[2,11,17,37,44,50,53,65,71,88,96,98,99,105,107,113,114,120,123,125,142,158,171,186,195,238,249,252,255,280,283,288,291,300,350,354,367,376,383,390,401,409,417,430,431,438,449,462,504,510,521,534,547,558,588,595,635,639,644,687,692,698,702,711,739,741,745,770,775,785,793,798,839,851,884,890,908,922,923,928,936,956,970,986,1011,1012,1015,1022,1025,1026,1029,1031,1037,1044,1073,1081,1084,1089,1100,1108,1112,1114,1136,1142,1171,1175,1182,1187,1190,1195,1227,1235,1240,1242,1247,1257,1264,1283,1285,1290,1295,1334,1339,1344,1346,1353,1366,1371,1385,1426,1437,1446,1473,1493,1499,1500,1500,1533,1535,1541,1556,1568,1598,1607,1620,1638,1654,1664,1708,1735,1750,1751,1780,1784,1787,1790,1793,1805,1826,1850,1868,1879,1886,1890,1896,1923,1927,1946,1966,1985,1986,2003,2025,2032,2033,2034,2036,2067,2071,2086,2088,2092,2094,2104,2129,2134,2147,2166,2220,2230,2241,2254,2257,2260,2283,2293,2309,2310,2322,2344,2354,2356,2365,2369,2395,2404,2408,2411,2415,2442,2463,2474,2478,2480,2482,2485,2502,2

gidim

{"metrics":[{"name":"acc","xSteps":[2,11,17,37,44,50,53,65,71,88,96,98,99,105,107,113,114,120,123,125,142,158,171,186,195,238,249,252,255,280,283,288,291,300,350,354,367,376,383,390,401,409,417,430,431,438,449,462,504,510,521,534,547,558,588,595,635,639,644,687,692,698,702,711,739,741,745,770,775,785,793,798,839,851,884,890,908,922,923,928,936,956,970,986,1011,1012,1015,1022,1025,1026,1029,1031,1037,1044,1073,1081,1084,1089,1100,1108,1112,1114,1136,1142,1171,1175,1182,1187,1190,1195,1227,1235,1240,1242,1247,1257,1264,1283,1285,1290,1295,1334,1339,1344,1346,1353,1366,1371,1385,1426,1437,1446,1473,1493,1499,1500,1500,1533,1535,1541,1556,1568,1598,1607,1620,1638,1654,1664,1708,1735,1750,1751,1780,1784,1787,1790,1793,1805,1826,1850,1868,1879,1886,1890,1896,1923,1927,1946,1966,1985,1986,2003,2025,2032,2033,2034,2036,2067,2071,2086,2088,2092,2094,2104,2129,2134,2147,2166,2220,2230,2241,2254,2257,2260,2283,2293,2309,2310,2322,2344,2354,2356,2365,2369,2395,2404,2408,2411,2415,2442,2463,2474,2478,2480,2482,2485,2502,2

gidim

import requests

access_token = "YOUR KEY HERE"

def get_projects():
	url = "https://www.comet.ml/api/rest/v1/projects"
	header = {"Authorization":  access_token}
	res = requests.get(url,headers=header)
	print(res.text)

gidim

First network (what you want)

computed(c,d)  |targets(c,d) |correct?
---------------------------------------------
0.66 0.33  | 1  0     | yes
0.66 0.33  | 1  0     | yes
0.66 0.33  | 0  1     | no

avg cross-entropy loss: 
-(ln(0.66) + ln(0.66) + ln(0.3)) / 3 = 0.678335

gidim

'''
A Dynamic Recurrent Neural Network (LSTM) implementation example using
TensorFlow library. This example is using a toy dataset to classify linear
sequences. The generated sequences have variable length.

Long Short Term Memory paper: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf

Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
'''