tx · BM7ehgNJjRxHo7mhrVujFVsbX5FhFkTyDeqeCDjJhPbY

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.04.28 11:47 [3082483] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "BM7ehgNJjRxHo7mhrVujFVsbX5FhFkTyDeqeCDjJhPbY",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1714294078020,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "2ARRCU9mKCd11NJEymBzPrWjEKVj2oQWL82sr2zn7sbAbNtA83QJpMJuL68g56bJxkvY3giHsRUhiutcQ1vfMpSa"
    ],
    "script": "base64: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",
    "height": 3082483,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: GY2gPoqivX3eeH3zPPj8SdvLMnbisXfuy2r24TQoJGgR
Next: BgXQzeibJ6sxd4Syjnb3oFzkazJ4kF1yu3ctYeGvh9Tu

Diff: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
-
let layer1Weights = [[600496, 600732], [414196, 414253]]
4
+
let layer1Weights = [[600497, 600732], [414197, 414253]]
5
5
 
6
6
 
let layer1Biases = [-259051, -635637]
7
7
 
10
10
 
let layer2Biases = [-381179]
11
11
 
12
12
 
func exp_approximation (x) = {
13
-
    let scale = 10000
13
+
    let scale = 100000
14
14
 
    let scaled_x = (x / scale)
15
-
    let e = 27183
15
+
    let e = 2718281
16
16
 
    let factor1 = scaled_x
17
17
 
    let factor2 = ((scaled_x * scaled_x) / (2 * scale))
18
18
 
    let factor3 = (((scaled_x * scaled_x) * scaled_x) / ((6 * scale) * scale))
19
-
    (((10000 + factor1) + factor2) + factor3)
19
+
    (((100000 + factor1) + factor2) + factor3)
20
20
 
    }
21
21
 
22
22
 
23
23
 
func sigmoid (z,debugPrefix) = {
24
-
    let base = 10000
24
+
    let base = 100000
25
25
 
    let positiveZ = if ((0 > z))
26
26
 
        then -(z)
27
27
 
        else z
28
28
 
    let expValue = exp_approximation(positiveZ)
29
-
    let sigValue = ((base * 10000) / (base + expValue))
29
+
    let sigValue = ((base * 100000) / (base + expValue))
30
30
 
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
31
31
 
    }
32
32
 
34
34
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
35
35
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
36
36
 
    let sum1 = ((fraction(input[0], weights[1][0], 1000000) + fraction(input[1], weights[1][1], 1000000)) + biases[1])
37
-
    let $t017111757 = sigmoid(sum0, "Layer1N0")
38
-
    let debug0 = $t017111757._1
39
-
    let sig0 = $t017111757._2
40
-
    let $t017621808 = sigmoid(sum1, "Layer1N1")
41
-
    let debug1 = $t017621808._1
42
-
    let sig1 = $t017621808._2
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
43
 
    $Tuple2([sig0, sig1], (debug0 ++ debug1))
44
44
 
    }
45
45
 
46
46
 
47
47
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
48
48
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
49
-
    let $t020772123 = sigmoid(sum0, "Layer2N0")
50
-
    let debug0 = $t020772123._1
51
-
    let sig0 = $t020772123._2
49
+
    let $t020552101 = sigmoid(sum0, "Layer2N0")
50
+
    let debug0 = $t020552101._1
51
+
    let sig0 = $t020552101._2
52
52
 
    $Tuple2(sig0, debug0)
53
53
 
    }
54
54
 
62
62
 
        then 1000000
63
63
 
        else 0
64
64
 
    let inputs = [scaledInput1, scaledInput2]
65
-
    let $t023742472 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
66
-
    let layer1Output = $t023742472._1
67
-
    let debugLayer1 = $t023742472._2
68
-
    let $t024772581 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
69
-
    let layer2Output = $t024772581._1
70
-
    let debugLayer2 = $t024772581._2
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
71
71
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
72
72
 
    }
73
73
 

Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
-
let layer1Weights = [[600496, 600732], [414196, 414253]]
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
12
 
func exp_approximation (x) = {
13
-
    let scale = 10000
13
+
    let scale = 100000
14
14
 
    let scaled_x = (x / scale)
15
-
    let e = 27183
15
+
    let e = 2718281
16
16
 
    let factor1 = scaled_x
17
17
 
    let factor2 = ((scaled_x * scaled_x) / (2 * scale))
18
18
 
    let factor3 = (((scaled_x * scaled_x) * scaled_x) / ((6 * scale) * scale))
19
-
    (((10000 + factor1) + factor2) + factor3)
19
+
    (((100000 + factor1) + factor2) + factor3)
20
20
 
    }
21
21
 
22
22
 
23
23
 
func sigmoid (z,debugPrefix) = {
24
-
    let base = 10000
24
+
    let base = 100000
25
25
 
    let positiveZ = if ((0 > z))
26
26
 
        then -(z)
27
27
 
        else z
28
28
 
    let expValue = exp_approximation(positiveZ)
29
-
    let sigValue = ((base * 10000) / (base + expValue))
29
+
    let sigValue = ((base * 100000) / (base + expValue))
30
30
 
    $Tuple2([IntegerEntry((debugPrefix + "positiveZ"), positiveZ), IntegerEntry((debugPrefix + "expValue"), expValue), IntegerEntry((debugPrefix + "sigValue"), sigValue)], sigValue)
31
31
 
    }
32
32
 
33
33
 
34
34
 
func forwardPassLayer1 (input,weights,biases,debugPrefix) = {
35
35
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
36
36
 
    let sum1 = ((fraction(input[0], weights[1][0], 1000000) + fraction(input[1], weights[1][1], 1000000)) + biases[1])
37
-
    let $t017111757 = sigmoid(sum0, "Layer1N0")
38
-
    let debug0 = $t017111757._1
39
-
    let sig0 = $t017111757._2
40
-
    let $t017621808 = sigmoid(sum1, "Layer1N1")
41
-
    let debug1 = $t017621808._1
42
-
    let sig1 = $t017621808._2
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
43
 
    $Tuple2([sig0, sig1], (debug0 ++ debug1))
44
44
 
    }
45
45
 
46
46
 
47
47
 
func forwardPassLayer2 (input,weights,biases,debugPrefix) = {
48
48
 
    let sum0 = ((fraction(input[0], weights[0][0], 1000000) + fraction(input[1], weights[0][1], 1000000)) + biases[0])
49
-
    let $t020772123 = sigmoid(sum0, "Layer2N0")
50
-
    let debug0 = $t020772123._1
51
-
    let sig0 = $t020772123._2
49
+
    let $t020552101 = sigmoid(sum0, "Layer2N0")
50
+
    let debug0 = $t020552101._1
51
+
    let sig0 = $t020552101._2
52
52
 
    $Tuple2(sig0, debug0)
53
53
 
    }
54
54
 
55
55
 
56
56
 
@Callable(i)
57
57
 
func predict (input1,input2) = {
58
58
 
    let scaledInput1 = if ((input1 == 1))
59
59
 
        then 1000000
60
60
 
        else 0
61
61
 
    let scaledInput2 = if ((input2 == 1))
62
62
 
        then 1000000
63
63
 
        else 0
64
64
 
    let inputs = [scaledInput1, scaledInput2]
65
-
    let $t023742472 = forwardPassLayer1(inputs, layer1Weights, layer1Biases, "Layer1")
66
-
    let layer1Output = $t023742472._1
67
-
    let debugLayer1 = $t023742472._2
68
-
    let $t024772581 = forwardPassLayer2(layer1Output, layer2Weights, layer2Biases, "Layer2")
69
-
    let layer2Output = $t024772581._1
70
-
    let debugLayer2 = $t024772581._2
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
71
71
 
    (([IntegerEntry("result", layer2Output)] ++ debugLayer1) ++ debugLayer2)
72
72
 
    }
73
73
 
74
74
 

github/deemru/w8io/6500d08 
146.38 ms ◑