tx · 8cdRbGHsNfmgK7NCToFRuLF7cqYNwNiYjBcET9w8VCPR

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.04.28 11:17 [3082456] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "8cdRbGHsNfmgK7NCToFRuLF7cqYNwNiYjBcET9w8VCPR",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1714292244171,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "4ckzcv7MqGWpU4esUzqCZnSpaZcN9pAuNma3r1921zntamA1e5t86rdALtzW85PzytyRnX2RY3fYLz1mt9gwuP5g"
    ],
    "script": "base64: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",
    "height": 3082456,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: HwyC8YbVJFQ1rUZWdjFea9Ep2RPaYKUJEWTMEip3U51S
Next: CTK5XZL5t8cmyyJ2vqgR2bTBcRpvXGeA2RrB6hGC8GVB

Diff: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
-
let layer1Weights = [[600497, 600732], [414197, 414252]]
4
+
let layer1Weights = [[600496, 600733], [414196, 414253]]
5
5
 
6
-
let layer1Biases = [-259051, -635637]
6
+
let layer1Biases = [-259050, -635637]
7
7
 
8
-
let layer2Weights = [[832966, -897141]]
8
+
let layer2Weights = [[832965, -897142]]
9
9
 
10
10
 
let layer2Biases = [-381179]
11
11
 
12
12
 
func exp_approximation (x) = {
13
-
    let e = 2718281
13
+
    let e = toBigInt(2718281)
14
14
 
    let factor1 = x
15
-
    let factor2 = fraction((x * x), (2 * 1000000), 1000000)
16
-
    let factor3 = fraction(((x * x) * x), ((6 * 1000000) * 1000000), 1000000)
17
-
    let exp_approx = (((1000000 + factor1) + factor2) + factor3)
18
-
    exp_approx
15
+
    let factor2 = fraction((x * x), toBigInt((2 * 1000000)), toBigInt(1000000))
16
+
    let factor3 = fraction(((x * x) * x), toBigInt(((6 * 1000000) * 1000000)), toBigInt(1000000))
17
+
    fraction((((toBigInt(1000000) + factor1) + factor2) + factor3), toBigInt(1), toBigInt(1))
19
18
 
    }
20
19
 
21
20
 
22
21
 
func sigmoid (z,debugPrefix) = {
23
-
    let base = 1000000
24
-
    let positiveZ = if ((0 > z))
22
+
    let base = toBigInt(1000000)
23
+
    let positiveZ = toBigInt(if ((0 > z))
25
24
 
        then -(z)
26
-
        else z
25
+
        else z)
27
26
 
    let expValue = exp_approximation(positiveZ)
28
-
    let sigValue = fraction(base, (base + expValue), base)
29
-
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
27
+
    let sigValue = fraction(base, (base + expValue), toBigInt(1))
28
+
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), toInt(positiveZ)), IntegerEntry((debugPrefix + "expValue"), toInt(expValue)), IntegerEntry((debugPrefix + "sigValue"), toInt(sigValue))], toInt(sigValue))
30
29
 
    }
31
30
 
32
31
 
33
32
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
34
33
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
35
34
 
    let sum1 = ((fraction(input[0], weights[1][0], 1000000) + fraction(input[1], weights[1][1], 1000000)) + biases[1])
36
-
    let $t013761422 = sigmoid(sum0, "Layer1N0")
37
-
    let debug0 = $t013761422._1
38
-
    let sig0 = $t013761422._2
39
-
    let $t014271473 = sigmoid(sum1, "Layer1N1")
40
-
    let debug1 = $t014271473._1
41
-
    let sig1 = $t014271473._2
35
+
    let $t015111557 = sigmoid(sum0, "Layer1N0")
36
+
    let debug0 = $t015111557._1
37
+
    let sig0 = $t015111557._2
38
+
    let $t015621608 = sigmoid(sum1, "Layer1N1")
39
+
    let debug1 = $t015621608._1
40
+
    let sig1 = $t015621608._2
42
41
 
    $Tuple2([sig0, sig1], (debug0 ++ debug1))
43
42
 
    }
44
43
 
45
44
 
46
45
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
47
46
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
48
-
    let $t017421788 = sigmoid(sum0, "Layer2N0")
49
-
    let debug0 = $t017421788._1
50
-
    let sig0 = $t017421788._2
47
+
    let $t018771923 = sigmoid(sum0, "Layer2N0")
48
+
    let debug0 = $t018771923._1
49
+
    let sig0 = $t018771923._2
51
50
 
    $Tuple2(sig0, debug0)
52
51
 
    }
53
52
 
61
60
 
        then 1000000
62
61
 
        else 0
63
62
 
    let inputs = [scaledInput1, scaledInput2]
64
-
    let $t020392137 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
65
-
    let layer1Output = $t020392137._1
66
-
    let debugLayer1 = $t020392137._2
67
-
    let $t021422246 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
68
-
    let layer2Output = $t021422246._1
69
-
    let debugLayer2 = $t021422246._2
63
+
    let $t021742272 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
64
+
    let layer1Output = $t021742272._1
65
+
    let debugLayer1 = $t021742272._2
66
+
    let $t022772381 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
67
+
    let layer2Output = $t022772381._1
68
+
    let debugLayer2 = $t022772381._2
70
69
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
71
70
 
    }
72
71
 

Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
-
let layer1Weights = [[600497, 600732], [414197, 414252]]
4
+
let layer1Weights = [[600496, 600733], [414196, 414253]]
5
5
 
6
-
let layer1Biases = [-259051, -635637]
6
+
let layer1Biases = [-259050, -635637]
7
7
 
8
-
let layer2Weights = [[832966, -897141]]
8
+
let layer2Weights = [[832965, -897142]]
9
9
 
10
10
 
let layer2Biases = [-381179]
11
11
 
12
12
 
func exp_approximation (x) = {
13
-
    let e = 2718281
13
+
    let e = toBigInt(2718281)
14
14
 
    let factor1 = x
15
-
    let factor2 = fraction((x * x), (2 * 1000000), 1000000)
16
-
    let factor3 = fraction(((x * x) * x), ((6 * 1000000) * 1000000), 1000000)
17
-
    let exp_approx = (((1000000 + factor1) + factor2) + factor3)
18
-
    exp_approx
15
+
    let factor2 = fraction((x * x), toBigInt((2 * 1000000)), toBigInt(1000000))
16
+
    let factor3 = fraction(((x * x) * x), toBigInt(((6 * 1000000) * 1000000)), toBigInt(1000000))
17
+
    fraction((((toBigInt(1000000) + factor1) + factor2) + factor3), toBigInt(1), toBigInt(1))
19
18
 
    }
20
19
 
21
20
 
22
21
 
func sigmoid (z,debugPrefix) = {
23
-
    let base = 1000000
24
-
    let positiveZ = if ((0 > z))
22
+
    let base = toBigInt(1000000)
23
+
    let positiveZ = toBigInt(if ((0 > z))
25
24
 
        then -(z)
26
-
        else z
25
+
        else z)
27
26
 
    let expValue = exp_approximation(positiveZ)
28
-
    let sigValue = fraction(base, (base + expValue), base)
29
-
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
27
+
    let sigValue = fraction(base, (base + expValue), toBigInt(1))
28
+
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), toInt(positiveZ)), IntegerEntry((debugPrefix + "expValue"), toInt(expValue)), IntegerEntry((debugPrefix + "sigValue"), toInt(sigValue))], toInt(sigValue))
30
29
 
    }
31
30
 
32
31
 
33
32
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
34
33
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
35
34
 
    let sum1 = ((fraction(input[0], weights[1][0], 1000000) + fraction(input[1], weights[1][1], 1000000)) + biases[1])
36
-
    let $t013761422 = sigmoid(sum0, "Layer1N0")
37
-
    let debug0 = $t013761422._1
38
-
    let sig0 = $t013761422._2
39
-
    let $t014271473 = sigmoid(sum1, "Layer1N1")
40
-
    let debug1 = $t014271473._1
41
-
    let sig1 = $t014271473._2
35
+
    let $t015111557 = sigmoid(sum0, "Layer1N0")
36
+
    let debug0 = $t015111557._1
37
+
    let sig0 = $t015111557._2
38
+
    let $t015621608 = sigmoid(sum1, "Layer1N1")
39
+
    let debug1 = $t015621608._1
40
+
    let sig1 = $t015621608._2
42
41
 
    $Tuple2([sig0, sig1], (debug0 ++ debug1))
43
42
 
    }
44
43
 
45
44
 
46
45
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
47
46
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
48
-
    let $t017421788 = sigmoid(sum0, "Layer2N0")
49
-
    let debug0 = $t017421788._1
50
-
    let sig0 = $t017421788._2
47
+
    let $t018771923 = sigmoid(sum0, "Layer2N0")
48
+
    let debug0 = $t018771923._1
49
+
    let sig0 = $t018771923._2
51
50
 
    $Tuple2(sig0, debug0)
52
51
 
    }
53
52
 
54
53
 
55
54
 
@Callable(i)
56
55
 
func predict (input1,input2) = {
57
56
 
    let scaledInput1 = if ((input1 == 1))
58
57
 
        then 1000000
59
58
 
        else 0
60
59
 
    let scaledInput2 = if ((input2 == 1))
61
60
 
        then 1000000
62
61
 
        else 0
63
62
 
    let inputs = [scaledInput1, scaledInput2]
64
-
    let $t020392137 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
65
-
    let layer1Output = $t020392137._1
66
-
    let debugLayer1 = $t020392137._2
67
-
    let $t021422246 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
68
-
    let layer2Output = $t021422246._1
69
-
    let debugLayer2 = $t021422246._2
63
+
    let $t021742272 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
64
+
    let layer1Output = $t021742272._1
65
+
    let debugLayer1 = $t021742272._2
66
+
    let $t022772381 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
67
+
    let layer2Output = $t022772381._1
68
+
    let debugLayer2 = $t022772381._2
70
69
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
71
70
 
    }
72
71
 
73
72
 

github/deemru/w8io/6500d08 
49.82 ms ◑