tx · FYY5e1t899S1xjoEgphoEeWuywfGRLTVAt65iBN8Pxv9

3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY:  -0.01000000 Waves

2024.05.26 22:09 [3123362] smart account 3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "FYY5e1t899S1xjoEgphoEeWuywfGRLTVAt65iBN8Pxv9",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1716750539690,
    "version": 2,
    "chainId": 84,
    "sender": "3N3n75UqB8G1GKmXFr4zPhKCjGcqJPRSuJY",
    "senderPublicKey": "2AWdnJuBMzufXSjTvzVcawBQQhnhF1iXR6QNVgwn33oc",
    "proofs": [
        "2qdkweuCvzG2Nn3VHBtU7C799U9TLti6Bdr5x1WtDec1HvGkuLeV4XBtGzwZ4qyXQuHTh7xvHHWcsx36b5Fp9msH"
    ],
    "script": "base64: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",
    "height": 3123362,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: 8bA5jMEQ6Vm9Rh4z9C9TER3GXZ2QKwTuAjWySbzGzVBv
Next: 6E7zaZ4wjSB9fjAqTL9Py14raWfez4jogsN994iBCpPg

Diff: 
Old
New
Differences
9
9
 
10
10
 
let biases_layer_2 = [-38117]
11
11
 
12
-
func linear_forward (input,weights,biases) = {
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
+
    }
17
+
18
+
19
+
func linear_forward_2 (input,weights,biases) = {
20
+
    let weighted_sum1 = ((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) / 10000) + biases[0])
21
+
[weighted_sum1]
16
22
 
    }
17
23
 
18
24
 
23
29
 
        else (5000 + (input / 2))
24
30
 
25
31
 
26
-
func sigmoid_activation (inputs) = [sigmoid(inputs[0]), sigmoid(inputs[1])]
32
+
func sigmoid_activation (inputs) = [sigmoid(inputs[0])]
27
33
 
28
34
 
29
35
 
@Callable(i)
31
37
 
    let x1_scaled = (x1 * 10000)
32
38
 
    let x2_scaled = (x2 * 10000)
33
39
 
    let inputs = [x1_scaled, x2_scaled]
34
-
    let z1 = linear_forward(inputs, weights_layer_1, biases_layer_1)
40
+
    let z1 = linear_forward_1(inputs, weights_layer_1, biases_layer_1)
35
41
 
    let a1 = sigmoid_activation(z1)
36
-
    let z2 = ((((a1[0] * weights_layer_2[0][0]) + (a1[1] * weights_layer_2[0][1])) / 10000) + biases_layer_2[0])
37
-
    let a2 = sigmoid(z2)
42
+
    let z2 = linear_forward_2(a1, weights_layer_2, biases_layer_2)
43
+
    let a2 = sigmoid(z2[0])
38
44
 
    let result = (a2 / 10000)
39
-
    let debug_outputs = [IntegerEntry("debug_z1_1", z1[0]), IntegerEntry("debug_a1_1", a1[0]), IntegerEntry("debug_z1_2", z1[1]), IntegerEntry("debug_a1_2", a1[1]), IntegerEntry("debug_a2", a2), IntegerEntry("debug_z2", z2), IntegerEntry("debug_result", result)]
45
+
    let debug_outputs = nil
40
46
 
    $Tuple2(debug_outputs, result)
41
47
 
    }
42
48
 

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
-
func linear_forward (input,weights,biases) = {
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
+
    }
17
+
18
+
19
+
func linear_forward_2 (input,weights,biases) = {
20
+
    let weighted_sum1 = ((((input[0] * weights[0][0]) + (input[1] * weights[0][1])) / 10000) + biases[0])
21
+
[weighted_sum1]
16
22
 
    }
17
23
 
18
24
 
19
25
 
func sigmoid (input) = if ((-10000 > input))
20
26
 
    then 0
21
27
 
    else if ((input > 10000))
22
28
 
        then 10000
23
29
 
        else (5000 + (input / 2))
24
30
 
25
31
 
26
-
func sigmoid_activation (inputs) = [sigmoid(inputs[0]), sigmoid(inputs[1])]
32
+
func sigmoid_activation (inputs) = [sigmoid(inputs[0])]
27
33
 
28
34
 
29
35
 
@Callable(i)
30
36
 
func predict (x1,x2) = {
31
37
 
    let x1_scaled = (x1 * 10000)
32
38
 
    let x2_scaled = (x2 * 10000)
33
39
 
    let inputs = [x1_scaled, x2_scaled]
34
-
    let z1 = linear_forward(inputs, weights_layer_1, biases_layer_1)
40
+
    let z1 = linear_forward_1(inputs, weights_layer_1, biases_layer_1)
35
41
 
    let a1 = sigmoid_activation(z1)
36
-
    let z2 = ((((a1[0] * weights_layer_2[0][0]) + (a1[1] * weights_layer_2[0][1])) / 10000) + biases_layer_2[0])
37
-
    let a2 = sigmoid(z2)
42
+
    let z2 = linear_forward_2(a1, weights_layer_2, biases_layer_2)
43
+
    let a2 = sigmoid(z2[0])
38
44
 
    let result = (a2 / 10000)
39
-
    let debug_outputs = [IntegerEntry("debug_z1_1", z1[0]), IntegerEntry("debug_a1_1", a1[0]), IntegerEntry("debug_z1_2", z1[1]), IntegerEntry("debug_a1_2", a1[1]), IntegerEntry("debug_a2", a2), IntegerEntry("debug_z2", z2), IntegerEntry("debug_result", result)]
45
+
    let debug_outputs = nil
40
46
 
    $Tuple2(debug_outputs, result)
41
47
 
    }
42
48
 
43
49
 

github/deemru/w8io/169f3d6 
39.03 ms ◑