tx · FPJLJBHCFpWbureEe13BzNSfQbZFGFP6nVQzTvxGcaVB

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.03.20 12:07 [3026144] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "FPJLJBHCFpWbureEe13BzNSfQbZFGFP6nVQzTvxGcaVB",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1710925713061,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "KwxhceLQVShJHbQbaaeqC6cwTwcGv1kk2VcykM2Bmddk1XSBDXySNodfnZUgg3eALj2npSnt7ZRwFx7hXDmUkj8"
    ],
    "script": "base64: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",
    "height": 3026144,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: Dt43XLUUf8BCJnkLcq3JC7kCQ4a6N3PTGwv5jeCvkDY2
Next: 2M6HVceMCCSxMt5DCypi4Uye6KUcaMYd3fZxBfo1itFh

Diff: 
Old
New
Differences
9
9
 
10
10
 
let layer2Biases = [3490942]
11
11
 
12
-
func sigmoid (z) = {
12
+
func sigmoid (z,debugPrefix) = {
13
13
 
    let e = 2718281
14
14
 
    let base = 1000000
15
15
 
    let negativeZ = (-1 * z)
16
16
 
    let expPart = fraction(e, negativeZ, base)
17
-
    fraction(base, base, (base + expPart))
17
+
    let sigValue = fraction(base, base, (base + expPart))
18
+
    $Tuple2([IntegerEntry((debugPrefix + "negativeZ"), negativeZ), IntegerEntry((debugPrefix + "expPart"), expPart)], sigValue)
18
19
 
    }
19
20
 
20
21
 
25
26
 
    }
26
27
 
27
28
 
28
-
func forwardPass (input,weights,biases) = {
29
+
func forwardPass (input,weights,biases,layer) = {
29
30
 
    let sum0 = (dotProduct(input, weights[0]) + biases[0])
30
31
 
    let sum1 = (dotProduct(input, weights[1]) + biases[1])
31
-
    let sig0 = sigmoid(sum0)
32
-
    let sig1 = sigmoid(sum1)
33
-
[sig0, sig1, sum0, sum1]
32
+
    let $t010051062 = sigmoid(sum0, (layer + "L1N1"))
33
+
    let sigmoidDebug0 = $t010051062._1
34
+
    let sig0 = $t010051062._2
35
+
    let $t010671124 = sigmoid(sum1, (layer + "L1N2"))
36
+
    let sigmoidDebug1 = $t010671124._1
37
+
    let sig1 = $t010671124._2
38
+
    $Tuple2([sig0, sig1, sum0, sum1], (sigmoidDebug0 ++ sigmoidDebug1))
34
39
 
    }
35
40
 
36
41
 
37
42
 
func xorNeuralNetwork (input1,input2) = {
38
43
 
    let input = [input1, input2]
39
-
    let hiddenLayerOutput = forwardPass(input, layer1Weights, layer1Biases)
40
-
    let outputLayerSum = (dotProduct([hiddenLayerOutput[0], hiddenLayerOutput[1]], layer2Weights[0]) + layer2Biases[0])
41
-
    let output = sigmoid(outputLayerSum)
42
-
[output, outputLayerSum, hiddenLayerOutput[2], hiddenLayerOutput[3]]
44
+
    let $t013021394 = forwardPass(input, layer1Weights, layer1Biases, "HL")
45
+
    let hiddenLayerOutput = $t013021394._1
46
+
    let hiddenDebug = $t013021394._2
47
+
    let $t013991534 = sigmoid((dotProduct([hiddenLayerOutput[0], hiddenLayerOutput[1]], layer2Weights[0]) + layer2Biases[0]), "OL")
48
+
    let outputDebug = $t013991534._1
49
+
    let output = $t013991534._2
50
+
    $Tuple2([output, (dotProduct([hiddenLayerOutput[0], hiddenLayerOutput[1]], layer2Weights[0]) + layer2Biases[0]), hiddenLayerOutput[2], hiddenLayerOutput[3]], (hiddenDebug ++ outputDebug))
43
51
 
    }
44
52
 
45
53
 
51
59
 
    let scaledInput2 = if ((input2 == 1))
52
60
 
        then 1000000
53
61
 
        else 0
54
-
    let networkOutputs = xorNeuralNetwork(scaledInput1, scaledInput2)
55
-
    let result = networkOutputs[0]
56
-
    let outputLayerSum = networkOutputs[1]
57
-
    let hiddenLayerOutput1Sum = networkOutputs[2]
58
-
    let hiddenLayerOutput2Sum = networkOutputs[3]
59
-
[IntegerEntry("result", result), IntegerEntry("outputLayerSum", outputLayerSum), IntegerEntry("hiddenLayerOutput1Sum", hiddenLayerOutput1Sum), IntegerEntry("hiddenLayerOutput2Sum", hiddenLayerOutput2Sum)]
62
+
    let $t019192000 = xorNeuralNetwork(scaledInput1, scaledInput2)
63
+
    let networkOutputs = $t019192000._1
64
+
    let debugEntries = $t019192000._2
65
+
    ([IntegerEntry("result", networkOutputs[0]), IntegerEntry("outputLayerSum", networkOutputs[1]), IntegerEntry("hiddenLayerOutput1Sum", networkOutputs[2]), IntegerEntry("hiddenLayerOutput2Sum", networkOutputs[3])] ++ debugEntries)
60
66
 
    }
61
67
 
62
68
 

Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
4
 
let layer1Weights = [[4721113, -5002107], [6226846, -6353789]]
5
5
 
6
6
 
let layer1Biases = [-2521378, 3389498]
7
7
 
8
8
 
let layer2Weights = [[8109936, -7559760]]
9
9
 
10
10
 
let layer2Biases = [3490942]
11
11
 
12
-
func sigmoid (z) = {
12
+
func sigmoid (z,debugPrefix) = {
13
13
 
    let e = 2718281
14
14
 
    let base = 1000000
15
15
 
    let negativeZ = (-1 * z)
16
16
 
    let expPart = fraction(e, negativeZ, base)
17
-
    fraction(base, base, (base + expPart))
17
+
    let sigValue = fraction(base, base, (base + expPart))
18
+
    $Tuple2([IntegerEntry((debugPrefix + "negativeZ"), negativeZ), IntegerEntry((debugPrefix + "expPart"), expPart)], sigValue)
18
19
 
    }
19
20
 
20
21
 
21
22
 
func dotProduct (a,b) = {
22
23
 
    let product0 = fraction(a[0], b[0], 1000000)
23
24
 
    let product1 = fraction(a[1], b[1], 1000000)
24
25
 
    (product0 + product1)
25
26
 
    }
26
27
 
27
28
 
28
-
func forwardPass (input,weights,biases) = {
29
+
func forwardPass (input,weights,biases,layer) = {
29
30
 
    let sum0 = (dotProduct(input, weights[0]) + biases[0])
30
31
 
    let sum1 = (dotProduct(input, weights[1]) + biases[1])
31
-
    let sig0 = sigmoid(sum0)
32
-
    let sig1 = sigmoid(sum1)
33
-
[sig0, sig1, sum0, sum1]
32
+
    let $t010051062 = sigmoid(sum0, (layer + "L1N1"))
33
+
    let sigmoidDebug0 = $t010051062._1
34
+
    let sig0 = $t010051062._2
35
+
    let $t010671124 = sigmoid(sum1, (layer + "L1N2"))
36
+
    let sigmoidDebug1 = $t010671124._1
37
+
    let sig1 = $t010671124._2
38
+
    $Tuple2([sig0, sig1, sum0, sum1], (sigmoidDebug0 ++ sigmoidDebug1))
34
39
 
    }
35
40
 
36
41
 
37
42
 
func xorNeuralNetwork (input1,input2) = {
38
43
 
    let input = [input1, input2]
39
-
    let hiddenLayerOutput = forwardPass(input, layer1Weights, layer1Biases)
40
-
    let outputLayerSum = (dotProduct([hiddenLayerOutput[0], hiddenLayerOutput[1]], layer2Weights[0]) + layer2Biases[0])
41
-
    let output = sigmoid(outputLayerSum)
42
-
[output, outputLayerSum, hiddenLayerOutput[2], hiddenLayerOutput[3]]
44
+
    let $t013021394 = forwardPass(input, layer1Weights, layer1Biases, "HL")
45
+
    let hiddenLayerOutput = $t013021394._1
46
+
    let hiddenDebug = $t013021394._2
47
+
    let $t013991534 = sigmoid((dotProduct([hiddenLayerOutput[0], hiddenLayerOutput[1]], layer2Weights[0]) + layer2Biases[0]), "OL")
48
+
    let outputDebug = $t013991534._1
49
+
    let output = $t013991534._2
50
+
    $Tuple2([output, (dotProduct([hiddenLayerOutput[0], hiddenLayerOutput[1]], layer2Weights[0]) + layer2Biases[0]), hiddenLayerOutput[2], hiddenLayerOutput[3]], (hiddenDebug ++ outputDebug))
43
51
 
    }
44
52
 
45
53
 
46
54
 
@Callable(i)
47
55
 
func predict (input1,input2) = {
48
56
 
    let scaledInput1 = if ((input1 == 1))
49
57
 
        then 1000000
50
58
 
        else 0
51
59
 
    let scaledInput2 = if ((input2 == 1))
52
60
 
        then 1000000
53
61
 
        else 0
54
-
    let networkOutputs = xorNeuralNetwork(scaledInput1, scaledInput2)
55
-
    let result = networkOutputs[0]
56
-
    let outputLayerSum = networkOutputs[1]
57
-
    let hiddenLayerOutput1Sum = networkOutputs[2]
58
-
    let hiddenLayerOutput2Sum = networkOutputs[3]
59
-
[IntegerEntry("result", result), IntegerEntry("outputLayerSum", outputLayerSum), IntegerEntry("hiddenLayerOutput1Sum", hiddenLayerOutput1Sum), IntegerEntry("hiddenLayerOutput2Sum", hiddenLayerOutput2Sum)]
62
+
    let $t019192000 = xorNeuralNetwork(scaledInput1, scaledInput2)
63
+
    let networkOutputs = $t019192000._1
64
+
    let debugEntries = $t019192000._2
65
+
    ([IntegerEntry("result", networkOutputs[0]), IntegerEntry("outputLayerSum", networkOutputs[1]), IntegerEntry("hiddenLayerOutput1Sum", networkOutputs[2]), IntegerEntry("hiddenLayerOutput2Sum", networkOutputs[3])] ++ debugEntries)
60
66
 
    }
61
67
 
62
68
 

github/deemru/w8io/6500d08 
22.23 ms ◑