tx · 6sK5SDfsLBqsGfy4qjtYGMKo72xqzbCSDcxVnRpEtrLn

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.05.04 12:27 [3091200] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "6sK5SDfsLBqsGfy4qjtYGMKo72xqzbCSDcxVnRpEtrLn",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1714814861757,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "3cCDQznVYEzXzQ696up9y3JgnMHcGSFm16LG5vxGbPLXMn3pmFtchv1PXs6BNDsuU29kr39m4qUgprdPirXLFPaV"
    ],
    "script": "base64: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",
    "height": 3091200,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: FZharDfu9u3yURdpNVPoqVoSWuAJo4VBm5dPLS1sNtbM
Next: 9o2vqzbv5JjJKboqkHfGhnn2XCjoXwLe8EaH4ffdKaSu

Diff: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
-
let layer1Weights = [[600496, 600733], [414197, 414253]]
4
+
let layer1Weights = [[4496, -6718], [36738, -36738], [3517, -3496], [-39880, 39880]]
5
5
 
6
-
let layer1Biases = [-259050, -635637]
6
+
let layer1Biases = [18719, -1, 29077, 0]
7
7
 
8
-
let layer2Weights = [[832966, -897141]]
8
+
let layer2Weights = [[-11902, 64358, -26901, 48391]]
9
9
 
10
-
let layer2Biases = [-381179]
10
+
let layer2Biases = [-6873]
11
11
 
12
12
 
func relu (x) = if ((x > 0))
13
13
 
    then x
33
33
 
                                else 10000
34
34
 
35
35
 
36
-
func dotProduct (v1,v2) = {
37
-
    let sum1 = ((v1[0] * v2[0]) / 10000)
38
-
    let sum2 = ((v1[1] * v2[1]) / 10000)
39
-
    (sum1 + sum2)
40
-
    }
36
+
func dotProduct (v1,v2) = (((v1[0] * v2[0]) + (v1[1] * v2[1])) / 10000)
41
37
 
42
38
 
43
39
 
func feedforward (inputs) = {
44
-
    let dp1 = dotProduct(inputs, layer1Weights[0])
45
-
    let dp2 = dotProduct(inputs, layer1Weights[1])
46
-
    let layer1Result1 = sigmoid_approx((dp1 + layer1Biases[0]))
47
-
    let layer1Result2 = sigmoid_approx((dp2 + layer1Biases[1]))
48
-
    let layer2Inputs = [layer1Result1, layer1Result2]
49
-
    let dp3 = dotProduct(layer2Inputs, layer2Weights[0])
50
-
    let output = sigmoid_approx((dp3 + layer2Biases[0]))
51
-
    $Tuple6(output, dp1, dp2, layer1Result1, layer1Result2, dp3)
40
+
    let dp1 = (dotProduct(inputs, layer1Weights[0]) + layer1Biases[0])
41
+
    let dp2 = (dotProduct(inputs, layer1Weights[1]) + layer1Biases[1])
42
+
    let dp3 = (dotProduct(inputs, layer1Weights[2]) + layer1Biases[2])
43
+
    let dp4 = (dotProduct(inputs, layer1Weights[3]) + layer1Biases[3])
44
+
    let layer1Results = [relu(dp1), relu(dp2), relu(dp3), relu(dp4)]
45
+
    let dpLayer2 = (dotProduct(layer1Results, layer2Weights[0]) + layer2Biases[0])
46
+
    sigmoid_approx(dpLayer2)
52
47
 
    }
53
48
 
54
49
 
55
50
 
@Callable(i)
56
51
 
func predict (input1,input2) = {
57
52
 
    let inputs = [input1, input2]
58
-
    let $t015191602 = feedforward(inputs)
59
-
    let prediction = $t015191602._1
60
-
    let dp1 = $t015191602._2
61
-
    let dp2 = $t015191602._3
62
-
    let layer1Result1 = $t015191602._4
63
-
    let layer1Result2 = $t015191602._5
64
-
    let dp3 = $t015191602._6
65
-
[IntegerEntry("prediction", prediction), IntegerEntry("dotProduct1", dp1), IntegerEntry("dotProduct2", dp2), IntegerEntry("layer1Result1", layer1Result1), IntegerEntry("layer1Result2", layer1Result2), IntegerEntry("dotProduct3", dp3)]
53
+
    let prediction = feedforward(inputs)
54
+
[IntegerEntry("prediction", prediction)]
66
55
 
    }
67
56
 
68
57
 

Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 5 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
-
let layer1Weights = [[600496, 600733], [414197, 414253]]
4
+
let layer1Weights = [[4496, -6718], [36738, -36738], [3517, -3496], [-39880, 39880]]
5
5
 
6
-
let layer1Biases = [-259050, -635637]
6
+
let layer1Biases = [18719, -1, 29077, 0]
7
7
 
8
-
let layer2Weights = [[832966, -897141]]
8
+
let layer2Weights = [[-11902, 64358, -26901, 48391]]
9
9
 
10
-
let layer2Biases = [-381179]
10
+
let layer2Biases = [-6873]
11
11
 
12
12
 
func relu (x) = if ((x > 0))
13
13
 
    then x
14
14
 
    else 0
15
15
 
16
16
 
17
17
 
func sigmoid_approx (x) = if ((-4000 > x))
18
18
 
    then 0
19
19
 
    else if ((-2000 > x))
20
20
 
        then 1000
21
21
 
        else if ((-1000 > x))
22
22
 
            then 2000
23
23
 
            else if ((0 > x))
24
24
 
                then 3000
25
25
 
                else if ((1000 > x))
26
26
 
                    then 5000
27
27
 
                    else if ((2000 > x))
28
28
 
                        then 7000
29
29
 
                        else if ((3000 > x))
30
30
 
                            then 8000
31
31
 
                            else if ((4000 > x))
32
32
 
                                then 9000
33
33
 
                                else 10000
34
34
 
35
35
 
36
-
func dotProduct (v1,v2) = {
37
-
    let sum1 = ((v1[0] * v2[0]) / 10000)
38
-
    let sum2 = ((v1[1] * v2[1]) / 10000)
39
-
    (sum1 + sum2)
40
-
    }
36
+
func dotProduct (v1,v2) = (((v1[0] * v2[0]) + (v1[1] * v2[1])) / 10000)
41
37
 
42
38
 
43
39
 
func feedforward (inputs) = {
44
-
    let dp1 = dotProduct(inputs, layer1Weights[0])
45
-
    let dp2 = dotProduct(inputs, layer1Weights[1])
46
-
    let layer1Result1 = sigmoid_approx((dp1 + layer1Biases[0]))
47
-
    let layer1Result2 = sigmoid_approx((dp2 + layer1Biases[1]))
48
-
    let layer2Inputs = [layer1Result1, layer1Result2]
49
-
    let dp3 = dotProduct(layer2Inputs, layer2Weights[0])
50
-
    let output = sigmoid_approx((dp3 + layer2Biases[0]))
51
-
    $Tuple6(output, dp1, dp2, layer1Result1, layer1Result2, dp3)
40
+
    let dp1 = (dotProduct(inputs, layer1Weights[0]) + layer1Biases[0])
41
+
    let dp2 = (dotProduct(inputs, layer1Weights[1]) + layer1Biases[1])
42
+
    let dp3 = (dotProduct(inputs, layer1Weights[2]) + layer1Biases[2])
43
+
    let dp4 = (dotProduct(inputs, layer1Weights[3]) + layer1Biases[3])
44
+
    let layer1Results = [relu(dp1), relu(dp2), relu(dp3), relu(dp4)]
45
+
    let dpLayer2 = (dotProduct(layer1Results, layer2Weights[0]) + layer2Biases[0])
46
+
    sigmoid_approx(dpLayer2)
52
47
 
    }
53
48
 
54
49
 
55
50
 
@Callable(i)
56
51
 
func predict (input1,input2) = {
57
52
 
    let inputs = [input1, input2]
58
-
    let $t015191602 = feedforward(inputs)
59
-
    let prediction = $t015191602._1
60
-
    let dp1 = $t015191602._2
61
-
    let dp2 = $t015191602._3
62
-
    let layer1Result1 = $t015191602._4
63
-
    let layer1Result2 = $t015191602._5
64
-
    let dp3 = $t015191602._6
65
-
[IntegerEntry("prediction", prediction), IntegerEntry("dotProduct1", dp1), IntegerEntry("dotProduct2", dp2), IntegerEntry("layer1Result1", layer1Result1), IntegerEntry("layer1Result2", layer1Result2), IntegerEntry("dotProduct3", dp3)]
53
+
    let prediction = feedforward(inputs)
54
+
[IntegerEntry("prediction", prediction)]
66
55
 
    }
67
56
 
68
57
 

github/deemru/w8io/6500d08 
26.56 ms ◑