tx · 5711d92xhrVacoLCGnr4ueRPQEShjH5WZkJkuy3oQGDY

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.06.10 00:49 [3143761] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "5711d92xhrVacoLCGnr4ueRPQEShjH5WZkJkuy3oQGDY",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1717969794872,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "5PBgCCSkCL8SzBdPraCTX6MBYKGZTBNi1c3zY5kPKNzxQXsEJZLVabFMtgNLzzfWfniJqSwobKrJTFGjcFXXt7Eh"
    ],
    "script": "base64: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",
    "height": 3143761,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: 8Z98WBSbg5ME521Bx7gZ74ugVt4yCFseUCkB5daWEzqE
Next: 8VVtUKLww8RFMZxyXTJzCbqcRAgJRfWJbWtuXA2dDDoU

Diff: 
Old
New
Differences
56
56
 
                                    else 10000
57
57
 
58
58
 
59
-
func sigmoid_activation (inputs,num_outputs) = if ((num_outputs == 1))
60
-
    then [sigmoid(inputs[0])]
61
-
    else [sigmoid(inputs[0]), sigmoid(inputs[1]), sigmoid(inputs[2]), sigmoid(inputs[3])]
59
+
func sigmoid_activation (inputs) = {
60
+
    let num_outputs = size(inputs)
61
+
    if ((num_outputs == 1))
62
+
        then [sigmoid(inputs[0])]
63
+
        else if ((num_outputs == 2))
64
+
            then [sigmoid(inputs[0]), sigmoid(inputs[1])]
65
+
            else [sigmoid(inputs[0]), sigmoid(inputs[1]), sigmoid(inputs[2]), sigmoid(inputs[3])]
66
+
    }
62
67
 
63
68
 
64
69
 
@Callable(i)
67
72
 
    let x2_scaled = (inputs[1] * 10000)
68
73
 
    let scaled_inputs = [x1_scaled, x2_scaled]
69
74
 
    let z1 = linear_forward_1(scaled_inputs, weights_layer_1, biases_layer_1)
70
-
    let a1 = sigmoid_activation(z1, 4)
75
+
    let a1 = sigmoid_activation(z1)
71
76
 
    let z2 = linear_forward_2(a1, weights_layer_2, biases_layer_2)
72
-
    let a2 = sigmoid_activation(z2, 2)
77
+
    let a2 = sigmoid_activation(z2)
73
78
 
    let z3 = linear_forward_3(a2, weights_layer_3, biases_layer_3)
74
-
    let a3 = sigmoid_activation(z3, 1)
79
+
    let a3 = sigmoid_activation(z3)
75
80
 
    let result0 = a3[0]
76
81
 
    let debug_outputs = nil
77
82
 
    ([IntegerEntry("move_prediction_0", result0)] ++ debug_outputs)
Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 7 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
4
 
let weights_layer_1 = [[-92752, 62221], [-92018, -65161], [-15287, 114503], [-75248, -60448]]
5
5
 
6
6
 
let biases_layer_1 = [-25696, 23125, -47529, 18951]
7
7
 
8
8
 
let weights_layer_2 = [[-75752, 55233, 65811, 37732], [68610, -57062, -60355, -33235]]
9
9
 
10
10
 
let biases_layer_2 = [-31616, 29450]
11
11
 
12
12
 
let weights_layer_3 = [[-89396, 95173]]
13
13
 
14
14
 
let biases_layer_3 = [-1923]
15
15
 
16
16
 
func linear_forward_1 (input,weights,biases) = {
17
17
 
    let weighted_sum1 = ((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) / 10000) + biases[0])
18
18
 
    let weighted_sum2 = ((((input[0] * weights[1][0]) + (input[1] * weights[1][1])) / 10000) + biases[1])
19
19
 
    let weighted_sum3 = ((((input[0] * weights[2][0]) + (input[1] * weights[2][1])) / 10000) + biases[2])
20
20
 
    let weighted_sum4 = ((((input[0] * weights[3][0]) + (input[1] * weights[3][1])) / 10000) + biases[3])
21
21
 
[weighted_sum1, weighted_sum2, weighted_sum3, weighted_sum4]
22
22
 
    }
23
23
 
24
24
 
25
25
 
func linear_forward_2 (input,weights,biases) = {
26
26
 
    let weighted_sum1 = ((((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) + (input[2] * weights[0][2])) + (input[3] * weights[0][3])) / 10000) + biases[0])
27
27
 
    let weighted_sum2 = ((((((input[0] * weights[1][0]) + (input[1] * weights[1][1])) + (input[2] * weights[1][2])) + (input[3] * weights[1][3])) / 10000) + biases[1])
28
28
 
[weighted_sum1, weighted_sum2]
29
29
 
    }
30
30
 
31
31
 
32
32
 
func linear_forward_3 (input,weights,biases) = {
33
33
 
    let weighted_sum1 = ((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) / 10000) + biases[0])
34
34
 
[weighted_sum1]
35
35
 
    }
36
36
 
37
37
 
38
38
 
func sigmoid (input) = if ((-80000 > input))
39
39
 
    then 0
40
40
 
    else if ((-60000 > input))
41
41
 
        then fraction((input + 80000), 125, 10000)
42
42
 
        else if ((-40000 > input))
43
43
 
            then fraction((input + 60000), 100, 10000)
44
44
 
            else if ((-20000 > input))
45
45
 
                then fraction((input + 40000), 75, 10000)
46
46
 
                else if ((0 > input))
47
47
 
                    then fraction((input + 20000), 50, 10000)
48
48
 
                    else if ((20000 > input))
49
49
 
                        then (fraction(input, 50, 10000) + 5000)
50
50
 
                        else if ((40000 > input))
51
51
 
                            then (fraction((input - 20000), 75, 10000) + 7500)
52
52
 
                            else if ((60000 > input))
53
53
 
                                then (fraction((input - 40000), 100, 10000) + 8750)
54
54
 
                                else if ((80000 > input))
55
55
 
                                    then (fraction((input - 60000), 125, 10000) + 9375)
56
56
 
                                    else 10000
57
57
 
58
58
 
59
-
func sigmoid_activation (inputs,num_outputs) = if ((num_outputs == 1))
60
-
    then [sigmoid(inputs[0])]
61
-
    else [sigmoid(inputs[0]), sigmoid(inputs[1]), sigmoid(inputs[2]), sigmoid(inputs[3])]
59
+
func sigmoid_activation (inputs) = {
60
+
    let num_outputs = size(inputs)
61
+
    if ((num_outputs == 1))
62
+
        then [sigmoid(inputs[0])]
63
+
        else if ((num_outputs == 2))
64
+
            then [sigmoid(inputs[0]), sigmoid(inputs[1])]
65
+
            else [sigmoid(inputs[0]), sigmoid(inputs[1]), sigmoid(inputs[2]), sigmoid(inputs[3])]
66
+
    }
62
67
 
63
68
 
64
69
 
@Callable(i)
65
70
 
func predict (inputs) = {
66
71
 
    let x1_scaled = (inputs[0] * 10000)
67
72
 
    let x2_scaled = (inputs[1] * 10000)
68
73
 
    let scaled_inputs = [x1_scaled, x2_scaled]
69
74
 
    let z1 = linear_forward_1(scaled_inputs, weights_layer_1, biases_layer_1)
70
-
    let a1 = sigmoid_activation(z1, 4)
75
+
    let a1 = sigmoid_activation(z1)
71
76
 
    let z2 = linear_forward_2(a1, weights_layer_2, biases_layer_2)
72
-
    let a2 = sigmoid_activation(z2, 2)
77
+
    let a2 = sigmoid_activation(z2)
73
78
 
    let z3 = linear_forward_3(a2, weights_layer_3, biases_layer_3)
74
-
    let a3 = sigmoid_activation(z3, 1)
79
+
    let a3 = sigmoid_activation(z3)
75
80
 
    let result0 = a3[0]
76
81
 
    let debug_outputs = nil
77
82
 
    ([IntegerEntry("move_prediction_0", result0)] ++ debug_outputs)
78
83
 
    }
79
84
 
80
85
 

github/deemru/w8io/169f3d6 
31.35 ms ◑