tx · 5p1i9rB1wwx7r6VVHGgpXzpPR7BQPZfUGxn9dP7VXG7j

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.06.09 18:39 [3143388] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "5p1i9rB1wwx7r6VVHGgpXzpPR7BQPZfUGxn9dP7VXG7j",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1717947626932,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "MnQrSZ3e2oogHwznx1WugtsXYRQBhwzB3A4DCV1ozmhKwjNELR7HGHVMfK7ZJH16JcS4oyDAmwknh8UGo612zvt"
    ],
    "script": "base64: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",
    "height": 3143388,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: iLK3jGMDmDhi5uY8BqmpYMqtqM7TxFQTu1SRiWqQRvW
Next: DYnXaheJEujNk48NpccmiJUvu9Ktv5oECHD7MeaRSt1d

Diff: 
Old
New
Differences
43
43
 
                                    else 10000
44
44
 
45
45
 
46
-
func sigmoid_activation (inputs,num_outputs) = [sigmoid(inputs[0]), sigmoid(inputs[1])]
46
+
func sigmoid_activation (inputs,num_outputs) = if ((num_outputs == 1))
47
+
    then [sigmoid(inputs[0])]
48
+
    else [sigmoid(inputs[0]), sigmoid(inputs[1])]
47
49
 
48
50
 
49
51
 
@Callable(i)
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 = [[60049, 60073], [41419, 41425]]
5
5
 
6
6
 
let biases_layer_1 = [-25905, -63563]
7
7
 
8
8
 
let weights_layer_2 = [[83296, -89714]]
9
9
 
10
10
 
let biases_layer_2 = [-38117]
11
11
 
12
12
 
func linear_forward_1 (input,weights,biases) = {
13
13
 
    let weighted_sum1 = ((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) / 10000) + biases[0])
14
14
 
    let weighted_sum2 = ((((input[0] * weights[1][0]) + (input[1] * weights[1][1])) / 10000) + biases[1])
15
15
 
[weighted_sum1, weighted_sum2]
16
16
 
    }
17
17
 
18
18
 
19
19
 
func linear_forward_2 (input,weights,biases) = {
20
20
 
    let weighted_sum1 = ((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) / 10000) + biases[0])
21
21
 
[weighted_sum1]
22
22
 
    }
23
23
 
24
24
 
25
25
 
func sigmoid (input) = if ((-80000 > input))
26
26
 
    then 0
27
27
 
    else if ((-60000 > input))
28
28
 
        then fraction((input + 80000), 125, 10000)
29
29
 
        else if ((-40000 > input))
30
30
 
            then fraction((input + 60000), 100, 10000)
31
31
 
            else if ((-20000 > input))
32
32
 
                then fraction((input + 40000), 75, 10000)
33
33
 
                else if ((0 > input))
34
34
 
                    then fraction((input + 20000), 50, 10000)
35
35
 
                    else if ((20000 > input))
36
36
 
                        then (fraction(input, 50, 10000) + 5000)
37
37
 
                        else if ((40000 > input))
38
38
 
                            then (fraction((input - 20000), 75, 10000) + 7500)
39
39
 
                            else if ((60000 > input))
40
40
 
                                then (fraction((input - 40000), 100, 10000) + 8750)
41
41
 
                                else if ((80000 > input))
42
42
 
                                    then (fraction((input - 60000), 125, 10000) + 9375)
43
43
 
                                    else 10000
44
44
 
45
45
 
46
-
func sigmoid_activation (inputs,num_outputs) = [sigmoid(inputs[0]), sigmoid(inputs[1])]
46
+
func sigmoid_activation (inputs,num_outputs) = if ((num_outputs == 1))
47
+
    then [sigmoid(inputs[0])]
48
+
    else [sigmoid(inputs[0]), sigmoid(inputs[1])]
47
49
 
48
50
 
49
51
 
@Callable(i)
50
52
 
func predict (inputs) = {
51
53
 
    let x1_scaled = (inputs[0] * 10000)
52
54
 
    let x2_scaled = (inputs[1] * 10000)
53
55
 
    let scaled_inputs = [x1_scaled, x2_scaled]
54
56
 
    let z1 = linear_forward_1(scaled_inputs, weights_layer_1, biases_layer_1)
55
57
 
    let a1 = sigmoid_activation(z1, 2)
56
58
 
    let z2 = linear_forward_2(a1, weights_layer_2, biases_layer_2)
57
59
 
    let a2 = sigmoid_activation(z2, 1)
58
60
 
    let result0 = a2[0]
59
61
 
    let debug_outputs = nil
60
62
 
    ([IntegerEntry("move_prediction_0", result0)] ++ debug_outputs)
61
63
 
    }
62
64
 
63
65
 

github/deemru/w8io/169f3d6 
30.16 ms ◑