tx · 2b25PWcsfJJqtzYdx5PHEx5557PpxguKVWbbsMW8ffgA

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.04.28 12:59 [3082559] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "2b25PWcsfJJqtzYdx5PHEx5557PpxguKVWbbsMW8ffgA",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1714298417301,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "ytP45QFEDTrqFyfLANC1rSgWhF5bLrBzSacJxfDsz42hh5A7wbPWW4jgcF8QDdm54LH2BUTH2QUcMHnVKB6kc4m"
    ],
    "script": "base64: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",
    "height": 3082559,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: EagziTUuatBGN4yrywpoprrknF46urgJ1q46iavxr1Ng
Next: 7s1h3jYoYnAwi8pPGmy5HUUL4Ybuoz6K6kVB7GwRyRrV

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, 414253]]
4
+
let layer1Weights = [[600496, 600733], [414196, 414253]]
5
5
 
6
6
 
let layer1Biases = [-259051, -635637]
7
7
 
8
8
 
let layer2Weights = [[832965, -897142]]
9
9
 
10
-
let layer2Biases = [-381178]
11
-
12
-
func exp_approx (x) = {
13
-
    let scale = 100000
14
-
    if (((-6 * scale) > x))
15
-
        then 1
16
-
        else if ((x > (6 * scale)))
17
-
            then 99999
18
-
            else {
19
-
                let coefficients = [$Tuple2(60000, 99999), $Tuple2(50000, 95000), $Tuple2(40000, 90000), $Tuple2(30000, 85000), $Tuple2(20000, 80000), $Tuple2(10000, 75000), $Tuple2(0, 70000), $Tuple2(-10000, 65000), $Tuple2(-20000, 60000), $Tuple2(-30000, 55000), $Tuple2(-40000, 50000), $Tuple2(-50000, 45000), $Tuple2(-60000, 40000)]
20
-
                let index = ((x + 60000) / 10000)
21
-
                let $t0920957 = coefficients[index]
22
-
                let blabla = $t0920957._1
23
-
                let y = $t0920957._2
24
-
                y
25
-
                }
26
-
    }
27
-
10
+
let layer2Biases = [-381179]
28
11
 
29
12
 
func sigmoid (z,debugPrefix) = {
30
-
    let base = 100000
13
+
    let e = 2718281
14
+
    let base = 1000000
31
15
 
    let positiveZ = if ((0 > z))
32
16
 
        then -(z)
33
17
 
        else z
34
-
    let expValue = exp_approx(positiveZ)
35
-
    let sigValue = ((base * expValue) / (base + expValue))
36
-
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
18
+
    let scaledZ = (positiveZ / 10000)
19
+
    let expPart = fraction(e, base, scaledZ)
20
+
    let sigValue = fraction(base, (base + expPart), base)
21
+
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expPart"), expPart), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
37
22
 
    }
38
23
 
39
24
 
40
25
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
41
26
 
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
42
27
 
    let sum1 = (((input[0] * weights[1][0]) + (input[1] * weights[1][1])) + (biases[1] * 100000))
43
-
    let $t017891842 = sigmoid(sum0, "Layer1N0")
44
-
    let debugEntries0 = $t017891842._1
45
-
    let sig0 = $t017891842._2
46
-
    let $t018471900 = sigmoid(sum1, "Layer1N1")
47
-
    let debugEntries1 = $t018471900._1
48
-
    let sig1 = $t018471900._2
28
+
    let $t011391192 = sigmoid(sum0, "Layer1N0")
29
+
    let debugEntries0 = $t011391192._1
30
+
    let sig0 = $t011391192._2
31
+
    let $t011971250 = sigmoid(sum1, "Layer1N1")
32
+
    let debugEntries1 = $t011971250._1
33
+
    let sig1 = $t011971250._2
49
34
 
    let debugInfo = (debugEntries0 ++ debugEntries1)
50
35
 
    let output = [sig0, sig1]
51
36
 
    $Tuple2(debugInfo, output)
54
39
 
55
40
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
56
41
 
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
57
-
    let $t022102263 = sigmoid(sum0, "Layer2N0")
58
-
    let debugEntries0 = $t022102263._1
59
-
    let sig0 = $t022102263._2
42
+
    let $t015601613 = sigmoid(sum0, "Layer2N0")
43
+
    let debugEntries0 = $t015601613._1
44
+
    let sig0 = $t015601613._2
60
45
 
    let debugInfo = debugEntries0
61
46
 
    let output = sig0
62
47
 
    $Tuple2(debugInfo, output)
72
57
 
        then 1000000
73
58
 
        else 0
74
59
 
    let inputs = [scaledInput1, scaledInput2]
75
-
    let $t025752673 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
76
-
    let debugLayer1 = $t025752673._1
77
-
    let layer1Output = $t025752673._2
78
-
    let $t026782782 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
79
-
    let debugLayer2 = $t026782782._1
80
-
    let layer2Output = $t026782782._2
60
+
    let $t019252023 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
61
+
    let debugLayer1 = $t019252023._1
62
+
    let layer1Output = $t019252023._2
63
+
    let $t020282132 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
64
+
    let debugLayer2 = $t020282132._1
65
+
    let layer2Output = $t020282132._2
81
66
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
82
67
 
    }
83
68
 

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, 414253]]
4
+
let layer1Weights = [[600496, 600733], [414196, 414253]]
5
5
 
6
6
 
let layer1Biases = [-259051, -635637]
7
7
 
8
8
 
let layer2Weights = [[832965, -897142]]
9
9
 
10
-
let layer2Biases = [-381178]
11
-
12
-
func exp_approx (x) = {
13
-
    let scale = 100000
14
-
    if (((-6 * scale) > x))
15
-
        then 1
16
-
        else if ((x > (6 * scale)))
17
-
            then 99999
18
-
            else {
19
-
                let coefficients = [$Tuple2(60000, 99999), $Tuple2(50000, 95000), $Tuple2(40000, 90000), $Tuple2(30000, 85000), $Tuple2(20000, 80000), $Tuple2(10000, 75000), $Tuple2(0, 70000), $Tuple2(-10000, 65000), $Tuple2(-20000, 60000), $Tuple2(-30000, 55000), $Tuple2(-40000, 50000), $Tuple2(-50000, 45000), $Tuple2(-60000, 40000)]
20
-
                let index = ((x + 60000) / 10000)
21
-
                let $t0920957 = coefficients[index]
22
-
                let blabla = $t0920957._1
23
-
                let y = $t0920957._2
24
-
                y
25
-
                }
26
-
    }
27
-
10
+
let layer2Biases = [-381179]
28
11
 
29
12
 
func sigmoid (z,debugPrefix) = {
30
-
    let base = 100000
13
+
    let e = 2718281
14
+
    let base = 1000000
31
15
 
    let positiveZ = if ((0 > z))
32
16
 
        then -(z)
33
17
 
        else z
34
-
    let expValue = exp_approx(positiveZ)
35
-
    let sigValue = ((base * expValue) / (base + expValue))
36
-
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
18
+
    let scaledZ = (positiveZ / 10000)
19
+
    let expPart = fraction(e, base, scaledZ)
20
+
    let sigValue = fraction(base, (base + expPart), base)
21
+
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expPart"), expPart), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
37
22
 
    }
38
23
 
39
24
 
40
25
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
41
26
 
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
42
27
 
    let sum1 = (((input[0] * weights[1][0]) + (input[1] * weights[1][1])) + (biases[1] * 100000))
43
-
    let $t017891842 = sigmoid(sum0, "Layer1N0")
44
-
    let debugEntries0 = $t017891842._1
45
-
    let sig0 = $t017891842._2
46
-
    let $t018471900 = sigmoid(sum1, "Layer1N1")
47
-
    let debugEntries1 = $t018471900._1
48
-
    let sig1 = $t018471900._2
28
+
    let $t011391192 = sigmoid(sum0, "Layer1N0")
29
+
    let debugEntries0 = $t011391192._1
30
+
    let sig0 = $t011391192._2
31
+
    let $t011971250 = sigmoid(sum1, "Layer1N1")
32
+
    let debugEntries1 = $t011971250._1
33
+
    let sig1 = $t011971250._2
49
34
 
    let debugInfo = (debugEntries0 ++ debugEntries1)
50
35
 
    let output = [sig0, sig1]
51
36
 
    $Tuple2(debugInfo, output)
52
37
 
    }
53
38
 
54
39
 
55
40
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
56
41
 
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
57
-
    let $t022102263 = sigmoid(sum0, "Layer2N0")
58
-
    let debugEntries0 = $t022102263._1
59
-
    let sig0 = $t022102263._2
42
+
    let $t015601613 = sigmoid(sum0, "Layer2N0")
43
+
    let debugEntries0 = $t015601613._1
44
+
    let sig0 = $t015601613._2
60
45
 
    let debugInfo = debugEntries0
61
46
 
    let output = sig0
62
47
 
    $Tuple2(debugInfo, output)
63
48
 
    }
64
49
 
65
50
 
66
51
 
@Callable(i)
67
52
 
func predict (input1,input2) = {
68
53
 
    let scaledInput1 = if ((input1 == 1))
69
54
 
        then 1000000
70
55
 
        else 0
71
56
 
    let scaledInput2 = if ((input2 == 1))
72
57
 
        then 1000000
73
58
 
        else 0
74
59
 
    let inputs = [scaledInput1, scaledInput2]
75
-
    let $t025752673 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
76
-
    let debugLayer1 = $t025752673._1
77
-
    let layer1Output = $t025752673._2
78
-
    let $t026782782 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
79
-
    let debugLayer2 = $t026782782._1
80
-
    let layer2Output = $t026782782._2
60
+
    let $t019252023 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
61
+
    let debugLayer1 = $t019252023._1
62
+
    let layer1Output = $t019252023._2
63
+
    let $t020282132 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
64
+
    let debugLayer2 = $t020282132._1
65
+
    let layer2Output = $t020282132._2
81
66
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
82
67
 
    }
83
68
 
84
69
 

github/deemru/w8io/6500d08 
48.51 ms ◑