tx · BgXQzeibJ6sxd4Syjnb3oFzkazJ4kF1yu3ctYeGvh9Tu

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.04.28 12:25 [3082524] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "BgXQzeibJ6sxd4Syjnb3oFzkazJ4kF1yu3ctYeGvh9Tu",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1714296352174,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "2ZF5hkjGjMUEhBxZyJpjRUWHn7ojG1f7pEJNGv2A8C8oKh53ws9hzxPXWSF4AXexMzSRLytLrv8j78p8CLiTxQrU"
    ],
    "script": "base64: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",
    "height": 3082524,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: BM7ehgNJjRxHo7mhrVujFVsbX5FhFkTyDeqeCDjJhPbY
Next: 3SS2H6aEuX3vuyY6DmmqnW7womLnia6zsZ7b9RdzwT5j

Diff: 
Old
New
Differences
9
9
 
10
10
 
let layer2Biases = [-381179]
11
11
 
12
-
func exp_approximation (x) = {
12
+
func exp_approx (x) = {
13
13
 
    let scale = 100000
14
-
    let scaled_x = (x / scale)
15
-
    let e = 2718281
16
-
    let factor1 = scaled_x
17
-
    let factor2 = ((scaled_x * scaled_x) / (2 * scale))
18
-
    let factor3 = (((scaled_x * scaled_x) * scaled_x) / ((6 * scale) * scale))
19
-
    (((100000 + factor1) + factor2) + factor3)
14
+
    if (((-6 * scale) > x))
15
+
        then 0
16
+
        else if ((x > (6 * scale)))
17
+
            then scale
18
+
            else {
19
+
                let coefficients = [$Tuple2(60000, 5000), $Tuple2(50000, 10000), $Tuple2(40000, 20000), $Tuple2(30000, 30000), $Tuple2(20000, 50000), $Tuple2(10000, 70000), $Tuple2(0, 100000), $Tuple2(-10000, 70000), $Tuple2(-20000, 50000), $Tuple2(-30000, 30000), $Tuple2(-40000, 20000), $Tuple2(-50000, 10000), $Tuple2(-60000, 5000)]
20
+
                let index = ((x + 60000) / 10000)
21
+
                let $t0811853 = coefficients[index]
22
+
                let coefficient = $t0811853._1
23
+
                let y = $t0811853._2
24
+
                y
25
+
                }
20
26
 
    }
21
27
 
22
28
 
25
31
 
    let positiveZ = if ((0 > z))
26
32
 
        then -(z)
27
33
 
        else z
28
-
    let expValue = exp_approximation(positiveZ)
29
-
    let sigValue = ((base * 100000) / (base + expValue))
34
+
    let expValue = exp_approx(positiveZ)
35
+
    let sigValue = ((base * base) / (base + expValue))
30
36
 
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
31
37
 
    }
32
38
 
33
39
 
34
40
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
35
-
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
36
-
    let sum1 = ((fraction(input[0], weights[1][0], 1000000) + fraction(input[1], weights[1][1], 1000000)) + biases[1])
37
-
    let $t016891735 = sigmoid(sum0, "Layer1N0")
38
-
    let debug0 = $t016891735._1
39
-
    let sig0 = $t016891735._2
40
-
    let $t017401786 = sigmoid(sum1, "Layer1N1")
41
-
    let debug1 = $t017401786._1
42
-
    let sig1 = $t017401786._2
43
-
    $Tuple2([sig0, sig1], (debug0 ++ debug1))
41
+
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
42
+
    let sum1 = (((input[0] * weights[1][0]) + (input[1] * weights[1][1])) + (biases[1] * 100000))
43
+
    let $t017231776 = sigmoid(sum0, "Layer1N0")
44
+
    let debugEntries0 = $t017231776._1
45
+
    let sig0 = $t017231776._2
46
+
    let $t017811834 = sigmoid(sum1, "Layer1N1")
47
+
    let debugEntries1 = $t017811834._1
48
+
    let sig1 = $t017811834._2
49
+
    let debugInfo = (debugEntries0 ++ debugEntries1)
50
+
    let output = [sig0, sig1]
51
+
    $Tuple2(debugInfo, output)
44
52
 
    }
45
53
 
46
54
 
47
55
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
48
-
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
49
-
    let $t020552101 = sigmoid(sum0, "Layer2N0")
50
-
    let debug0 = $t020552101._1
51
-
    let sig0 = $t020552101._2
52
-
    $Tuple2(sig0, debug0)
56
+
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
57
+
    let $t021442197 = sigmoid(sum0, "Layer2N0")
58
+
    let debugEntries0 = $t021442197._1
59
+
    let sig0 = $t021442197._2
60
+
    let debugInfo = debugEntries0
61
+
    let output = sig0
62
+
    $Tuple2(debugInfo, output)
53
63
 
    }
54
64
 
55
65
 
62
72
 
        then 1000000
63
73
 
        else 0
64
74
 
    let inputs = [scaledInput1, scaledInput2]
65
-
    let $t023522450 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
66
-
    let layer1Output = $t023522450._1
67
-
    let debugLayer1 = $t023522450._2
68
-
    let $t024552559 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
69
-
    let layer2Output = $t024552559._1
70
-
    let debugLayer2 = $t024552559._2
75
+
    let $t025092607 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
76
+
    let debugLayer1 = $t025092607._1
77
+
    let layer1Output = $t025092607._2
78
+
    let $t026122716 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
79
+
    let debugLayer2 = $t026122716._1
80
+
    let layer2Output = $t026122716._2
71
81
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
72
82
 
    }
73
83
 

Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
4
 
let layer1Weights = [[600497, 600732], [414197, 414253]]
5
5
 
6
6
 
let layer1Biases = [-259051, -635637]
7
7
 
8
8
 
let layer2Weights = [[832965, -897142]]
9
9
 
10
10
 
let layer2Biases = [-381179]
11
11
 
12
-
func exp_approximation (x) = {
12
+
func exp_approx (x) = {
13
13
 
    let scale = 100000
14
-
    let scaled_x = (x / scale)
15
-
    let e = 2718281
16
-
    let factor1 = scaled_x
17
-
    let factor2 = ((scaled_x * scaled_x) / (2 * scale))
18
-
    let factor3 = (((scaled_x * scaled_x) * scaled_x) / ((6 * scale) * scale))
19
-
    (((100000 + factor1) + factor2) + factor3)
14
+
    if (((-6 * scale) > x))
15
+
        then 0
16
+
        else if ((x > (6 * scale)))
17
+
            then scale
18
+
            else {
19
+
                let coefficients = [$Tuple2(60000, 5000), $Tuple2(50000, 10000), $Tuple2(40000, 20000), $Tuple2(30000, 30000), $Tuple2(20000, 50000), $Tuple2(10000, 70000), $Tuple2(0, 100000), $Tuple2(-10000, 70000), $Tuple2(-20000, 50000), $Tuple2(-30000, 30000), $Tuple2(-40000, 20000), $Tuple2(-50000, 10000), $Tuple2(-60000, 5000)]
20
+
                let index = ((x + 60000) / 10000)
21
+
                let $t0811853 = coefficients[index]
22
+
                let coefficient = $t0811853._1
23
+
                let y = $t0811853._2
24
+
                y
25
+
                }
20
26
 
    }
21
27
 
22
28
 
23
29
 
func sigmoid (z,debugPrefix) = {
24
30
 
    let base = 100000
25
31
 
    let positiveZ = if ((0 > z))
26
32
 
        then -(z)
27
33
 
        else z
28
-
    let expValue = exp_approximation(positiveZ)
29
-
    let sigValue = ((base * 100000) / (base + expValue))
34
+
    let expValue = exp_approx(positiveZ)
35
+
    let sigValue = ((base * base) / (base + expValue))
30
36
 
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
31
37
 
    }
32
38
 
33
39
 
34
40
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
35
-
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
36
-
    let sum1 = ((fraction(input[0], weights[1][0], 1000000) + fraction(input[1], weights[1][1], 1000000)) + biases[1])
37
-
    let $t016891735 = sigmoid(sum0, "Layer1N0")
38
-
    let debug0 = $t016891735._1
39
-
    let sig0 = $t016891735._2
40
-
    let $t017401786 = sigmoid(sum1, "Layer1N1")
41
-
    let debug1 = $t017401786._1
42
-
    let sig1 = $t017401786._2
43
-
    $Tuple2([sig0, sig1], (debug0 ++ debug1))
41
+
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
42
+
    let sum1 = (((input[0] * weights[1][0]) + (input[1] * weights[1][1])) + (biases[1] * 100000))
43
+
    let $t017231776 = sigmoid(sum0, "Layer1N0")
44
+
    let debugEntries0 = $t017231776._1
45
+
    let sig0 = $t017231776._2
46
+
    let $t017811834 = sigmoid(sum1, "Layer1N1")
47
+
    let debugEntries1 = $t017811834._1
48
+
    let sig1 = $t017811834._2
49
+
    let debugInfo = (debugEntries0 ++ debugEntries1)
50
+
    let output = [sig0, sig1]
51
+
    $Tuple2(debugInfo, output)
44
52
 
    }
45
53
 
46
54
 
47
55
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
48
-
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
49
-
    let $t020552101 = sigmoid(sum0, "Layer2N0")
50
-
    let debug0 = $t020552101._1
51
-
    let sig0 = $t020552101._2
52
-
    $Tuple2(sig0, debug0)
56
+
    let sum0 = (((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (biases[0] * 100000))
57
+
    let $t021442197 = sigmoid(sum0, "Layer2N0")
58
+
    let debugEntries0 = $t021442197._1
59
+
    let sig0 = $t021442197._2
60
+
    let debugInfo = debugEntries0
61
+
    let output = sig0
62
+
    $Tuple2(debugInfo, output)
53
63
 
    }
54
64
 
55
65
 
56
66
 
@Callable(i)
57
67
 
func predict (input1,input2) = {
58
68
 
    let scaledInput1 = if ((input1 == 1))
59
69
 
        then 1000000
60
70
 
        else 0
61
71
 
    let scaledInput2 = if ((input2 == 1))
62
72
 
        then 1000000
63
73
 
        else 0
64
74
 
    let inputs = [scaledInput1, scaledInput2]
65
-
    let $t023522450 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
66
-
    let layer1Output = $t023522450._1
67
-
    let debugLayer1 = $t023522450._2
68
-
    let $t024552559 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
69
-
    let layer2Output = $t024552559._1
70
-
    let debugLayer2 = $t024552559._2
75
+
    let $t025092607 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
76
+
    let debugLayer1 = $t025092607._1
77
+
    let layer1Output = $t025092607._2
78
+
    let $t026122716 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
79
+
    let debugLayer2 = $t026122716._1
80
+
    let layer2Output = $t026122716._2
71
81
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
72
82
 
    }
73
83
 
74
84
 

github/deemru/w8io/6500d08 
33.32 ms ◑