tx · 7TxoJfzsmTY4kCjXtwb4Rrio9Vm5m292D5RKdp53fR9B

3Moz6HJhucpFh4V3VScXhd9efei4Curytfj:  -0.01000000 Waves

2023.10.28 17:52 [2818629] smart account 3Moz6HJhucpFh4V3VScXhd9efei4Curytfj > SELF 0.00000000 Waves

{
    "type": 13,
    "id": "7TxoJfzsmTY4kCjXtwb4Rrio9Vm5m292D5RKdp53fR9B",
    "fee": 1000000,
    "feeAssetId": null,
    "timestamp": 1698504827006,
    "version": 2,
    "chainId": 84,
    "sender": "3Moz6HJhucpFh4V3VScXhd9efei4Curytfj",
    "senderPublicKey": "Ec1VLg3r1E7mwHmaNidmoKrFAUJ55UVJFq3J1YKRy5Zm",
    "proofs": [
        "5uffz4NGnTfeNm8jiP7WQB2NTfvUEAwap1bkp2KWTbroSBqkiyWRmuUssNUGEDaUU6mjySmQiJaV27J2ZzkR6frk"
    ],
    "script": "base64:BgIHCAISAwoBEQwAB3NwZWNpZXMJAMwIAgILSXJpcy1zZXRvc2EJAMwIAgIPSXJpcy12ZXJzaWNvbG9yCQDMCAICDklyaXMtdmlyZ2luaWNhBQNuaWwAB3dlaWdodDEJAMwIAgkAzAgCAI0wCQDMCAIAhuj/////////AQkAzAgCAMZeCQDMCAIAmYcBBQNuaWwJAMwIAgkAzAgCAKDh/////////wEJAMwIAgD36/////////8BCQDMCAIAgOr/////////AQkAzAgCAIgDBQNuaWwJAMwIAgkAzAgCAOkzCQDMCAIArAIJAMwIAgCrWQkAzAgCAKVbBQNuaWwJAMwIAgkAzAgCALUgCQDMCAIAodn/////////AQkAzAgCAM/n/////////wEJAMwIAgCVBwUDbmlsCQDMCAIJAMwIAgCmMQkAzAgCALq3/////////wEJAMwIAgDERAkAzAgCAIoCBQNuaWwJAMwIAgkAzAgCAPH7/////////wEJAMwIAgDqKwkAzAgCANXo/////////wEJAMwIAgDNnf////////8BBQNuaWwJAMwIAgkAzAgCAMw2CQDMCAIAw9T/////////AQkAzAgCAPlZCQDMCAIA/XIFA25pbAkAzAgCCQDMCAIAgBUJAMwIAgCvLgkAzAgCALi1/////////wEJAMwIAgCIu/////////8BBQNuaWwJAMwIAgkAzAgCAKoSCQDMCAIApDQJAMwIAgCTzv////////8BCQDMCAIArJj/////////AQUDbmlsCQDMCAIJAMwIAgDkFgkAzAgCAPpUCQDMCAIAorH/////////AQkAzAgCAJSp/////////wEFA25pbAkAzAgCCQDMCAIAx+b/////////AQkAzAgCAJqUAQkAzAgCANaU/////////wEJAMwIAgCs7v7///////8BBQNuaWwJAMwIAgkAzAgCAK1TCQDMCAIA7sj/////////AQkAzAgCAL+DAQkAzAgCALuHAQUDbmlsBQNuaWwAB2JpYXNlczEJAMwIAgCR7v////////8BCQDMCAIA0Ob/////////AQkAzAgCAL7V/////////wEJAMwIAgCe4v////////8BCQDMCAIA8xwJAMwIAgDvWwkAzAgCAP/1/////////wEJAMwIAgCGWAkAzAgCAINjCQDMCAIA6F0JAMwIAgCNVAkAzAgCALzv/////////wEFA25pbAAHd2VpZ2h0MgkAzAgCCQDMCAIAvZL/////////AQkAzAgCANb+/////////wEJAMwIAgCYmv////////8BCQDMCAIAiBMJAMwIAgCjpP////////8BCQDMCAIAy2sJAMwIAgCzh/////////8BCQDMCAIAwGMJAMwIAgD0agkAzAgCAPJzCQDMCAIA8Y4BCQDMCAIAnp7/////////AQUDbmlsCQDMCAIJAMwIAgDt+f////////8BCQDMCAIAjQQJAMwIAgDW1P////////8BCQDMCAIA5P//////////AQkAzAgCAMIdCQDMCAIA0nIJAMwIAgDKAgkAzAgCAMJ4CQDMCAIAs2sJAMwIAgCXTgkAzAgCAKja/v///////wEJAMwIAgDRAwUDbmlsCQDMCAIJAMwIAgChMAkAzAgCAMUICQDMCAIAsEsJAMwIAgChDgkAzAgCALcKCQDMCAIAg97+////////AQkAzAgCAMY1CQDMCAIA17f+////////AQkAzAgCAJ26/v///////wEJAMwIAgCy8P7///////8BCQDMCAIAoLz/////////AQkAzAgCAKI8BQNuaWwFA25pbAAFYmlhczIJAMwIAgC3MwkAzAgCAMgyCQDMCAIAjNz/////////AQUDbmlsAQRyZWx1AQF4AwkAZgIFAXgAAAUBeAAAAQRjYWxjAwVpbnB1dAZ3ZWlnaHQEYmlhcwQEY2FsYwkAZAIJAGQCCQBkAgkAZAIJAGgCCQCRAwIFBWlucHV0AAAJAJEDAgUGd2VpZ2h0AAAJAGgCCQCRAwIFBWlucHV0AAEJAJEDAgUGd2VpZ2h0AAEJAGgCCQCRAwIFBWlucHV0AAIJAJEDAgUGd2VpZ2h0AAIJAGgCCQCRAwIFBWlucHV0AAMJAJEDAgUGd2VpZ2h0AAMFBGJpYXMFBGNhbGMBEWNhbGNfc2Vjb25kX2xheWVyAwVpbnB1dAZ3ZWlnaHQEYmlhcwQLY2FsY19zZWNvbmQJAGQCCQBkAgkAZAIJAGQCCQBkAgkAZAIJAGQCCQBkAgkAZAIJAGQCCQBkAgkAZAIJAGgCCQCRAwIFBWlucHV0AAAJAJEDAgUGd2VpZ2h0AAAJAGgCCQCRAwIFBWlucHV0AAEJAJEDAgUGd2VpZ2h0AAEJAGgCCQCRAwIFBWlucHV0AAIJAJEDAgUGd2VpZ2h0AAIJAGgCCQCRAwIFBWlucHV0AAMJAJEDAgUGd2VpZ2h0AAMJAGgCCQCRAwIFBWlucHV0AAQJAJEDAgUGd2VpZ2h0AAQJAGgCCQCRAwIFBWlucHV0AAUJAJEDAgUGd2VpZ2h0AAUJAGgCCQCRAwIFBWlucHV0AAYJAJEDAgUGd2VpZ2h0AAYJAGgCCQCRAwIFBWlucHV0AAcJAJEDAgUGd2VpZ2h0AAcJAGgCCQCRAwIFBWlucHV0AAgJAJEDAgUGd2VpZ2h0AAgJAGgCCQCRAwIFBWlucHV0AAkJAJEDAgUGd2VpZ2h0AAkJAGgCCQCRAwIFBWlucHV0AAoJAJEDAgUGd2VpZ2h0AAoJAGgCCQCRAwIFBWlucHV0AAsJAJEDAgUGd2VpZ2h0AAsFBGJpYXMFC2NhbGNfc2Vjb25kARNjYWxjdWxhdGVGaXJzdExheWVyAQVpbnB1dAQNb3V0cHV0X2xheWVyMQkBBHJlbHUBCQEEY2FsYwMFBWlucHV0CQCRAwIFB3dlaWdodDEAAAkAkQMCBQdiaWFzZXMxAAAEDW91dHB1dF9sYXllcjIJAQRyZWx1AQkBBGNhbGMDBQVpbnB1dAkAkQMCBQd3ZWlnaHQxAAEJAJEDAgUHYmlhc2VzMQABBA1vdXRwdXRfbGF5ZXIzCQEEcmVsdQEJAQRjYWxjAwUFaW5wdXQJAJEDAgUHd2VpZ2h0MQACCQCRAwIFB2JpYXNlczEAAgQNb3V0cHV0X2xheWVyNAkBBHJlbHUBCQEEY2FsYwMFBWlucHV0CQCRAwIFB3dlaWdodDEAAwkAkQMCBQdiaWFzZXMxAAMEDW91dHB1dF9sYXllcjUJAQRyZWx1AQkBBGNhbGMDBQVpbnB1dAkAkQMCBQd3ZWlnaHQxAAQJAJEDAgUHYmlhc2VzMQAEBA1vdXRwdXRfbGF5ZXI2CQEEcmVsdQEJAQRjYWxjAwUFaW5wdXQJAJEDAgUHd2VpZ2h0MQAFCQCRAwIFB2JpYXNlczEABQQNb3V0cHV0X2xheWVyNwkBBHJlbHUBCQEEY2FsYwMFBWlucHV0CQCRAwIFB3dlaWdodDEABgkAkQMCBQdiaWFzZXMxAAYEDW91dHB1dF9sYXllcjgJAQRyZWx1AQkBBGNhbGMDBQVpbnB1dAkAkQMCBQd3ZWlnaHQxAAcJAJEDAgUHYmlhc2VzMQAHBA1vdXRwdXRfbGF5ZXI5CQEEcmVsdQEJAQRjYWxjAwUFaW5wdXQJAJEDAgUHd2VpZ2h0MQAICQCRAwIFB2JpYXNlczEACAQOb3V0cHV0X2xheWVyMTAJAQRyZWx1AQkBBGNhbGMDBQVpbnB1dAkAkQMCBQd3ZWlnaHQxAAkJAJEDAgUHYmlhc2VzMQAJBA5vdXRwdXRfbGF5ZXIxMQkBBHJlbHUBCQEEY2FsYwMFBWlucHV0CQCRAwIFB3dlaWdodDEACgkAkQMCBQdiaWFzZXMxAAoEDm91dHB1dF9sYXllcjEyCQEEcmVsdQEJAQRjYWxjAwUFaW5wdXQJAJEDAgUHd2VpZ2h0MQALCQCRAwIFB2JpYXNlczEACwkAzAgCBQ1vdXRwdXRfbGF5ZXIxCQDMCAIFDW91dHB1dF9sYXllcjIJAMwIAgUNb3V0cHV0X2xheWVyMwkAzAgCBQ1vdXRwdXRfbGF5ZXI0CQDMCAIFDW91dHB1dF9sYXllcjUJAMwIAgUNb3V0cHV0X2xheWVyNgkAzAgCBQ1vdXRwdXRfbGF5ZXI3CQDMCAIFDW91dHB1dF9sYXllcjgJAMwIAgUNb3V0cHV0X2xheWVyOQkAzAgCBQ5vdXRwdXRfbGF5ZXIxMAkAzAgCBQ5vdXRwdXRfbGF5ZXIxMQkAzAgCBQ5vdXRwdXRfbGF5ZXIxMgUDbmlsARRjYWxjdWxhdGVTZWNvbmRMYXllcgEFaW5wdXQEDW91dHB1dF9sYXllcjEJARFjYWxjX3NlY29uZF9sYXllcgMFBWlucHV0CQCRAwIFB3dlaWdodDIAAAkAkQMCBQViaWFzMgAABA1vdXRwdXRfbGF5ZXIyCQERY2FsY19zZWNvbmRfbGF5ZXIDBQVpbnB1dAkAkQMCBQd3ZWlnaHQyAAEJAJEDAgUFYmlhczIAAQQNb3V0cHV0X2xheWVyMwkBEWNhbGNfc2Vjb25kX2xheWVyAwUFaW5wdXQJAJEDAgUHd2VpZ2h0MgACCQCRAwIFBWJpYXMyAAIJAMwIAgUNb3V0cHV0X2xheWVyMQkAzAgCBQ1vdXRwdXRfbGF5ZXIyCQDMCAIFDW91dHB1dF9sYXllcjMFA25pbAEMZm9yd2FyZF9wcm9wAQVpbnB1dAQLZmlyc3RfbGF5ZXIJARNjYWxjdWxhdGVGaXJzdExheWVyAQUFaW5wdXQEDHNlY29uZF9sYXllcgkBFGNhbGN1bGF0ZVNlY29uZExheWVyAQULZmlyc3RfbGF5ZXIFDHNlY29uZF9sYXllcgEJZmluZF9wcmVkAQZvdXRwdXQEBG1heDEDCQBmAgkAkQMCBQZvdXRwdXQAAAkAkQMCBQZvdXRwdXQAAQAAAAEEBG1heDIDCQBmAgUEbWF4MQkAkQMCBQZvdXRwdXQAAgUEbWF4MQACBQRtYXgyAQFpAQpwcmVkaWN0aW9uAQVpbnB1dAQGb3V0cHV0CQEMZm9yd2FyZF9wcm9wAQUFaW5wdXQEDWNhbGxlckFkZHJlc3MJAKUIAQgFAWkGY2FsbGVyBARwcmVkCQEJZmluZF9wcmVkAQUGb3V0cHV0CQDMCAIJAQxJbnRlZ2VyRW50cnkCCQCsAgIFDWNhbGxlckFkZHJlc3MCAl8xCQCRAwIFBm91dHB1dAAACQDMCAIJAQxJbnRlZ2VyRW50cnkCCQCsAgIFDWNhbGxlckFkZHJlc3MCAl8yCQCRAwIFBm91dHB1dAABCQDMCAIJAQxJbnRlZ2VyRW50cnkCCQCsAgIFDWNhbGxlckFkZHJlc3MCAl8zCQCRAwIFBm91dHB1dAACCQDMCAIJAQtTdHJpbmdFbnRyeQIJAKwCAgUNY2FsbGVyQWRkcmVzcwICX3AJAJEDAgUHc3BlY2llcwUEcHJlZAUDbmlsAICFX34=",
    "height": 2818629,
    "applicationStatus": "succeeded",
    "spentComplexity": 0
}

View: original | compacted
Prev: 3yXAAVQ7hMyV4mpM7j8V8iJYvsLoYdyi3DGY5qod2bQT
Next: edHHWZhzMocFaEmRgCHdG39rnEcosEpcE9P1JVNUaNo

Diff: 
Old
New
Differences
29
29
 
30
30
 
31
31
 
func calculateFirstLayer (input) = {
32
-
    let ouput_layer1 = relu(calc(input, weight1[0], biases1[0]))
33
-
    let ouput_layer2 = relu(calc(input, weight1[1], biases1[1]))
34
-
    let ouput_layer3 = relu(calc(input, weight1[2], biases1[2]))
35
-
    let ouput_layer4 = relu(calc(input, weight1[3], biases1[3]))
36
-
    let ouput_layer5 = relu(calc(input, weight1[4], biases1[4]))
37
-
    let ouput_layer6 = relu(calc(input, weight1[5], biases1[5]))
38
-
    let ouput_layer7 = relu(calc(input, weight1[6], biases1[6]))
39
-
    let ouput_layer8 = relu(calc(input, weight1[7], biases1[7]))
40
-
    let ouput_layer9 = relu(calc(input, weight1[8], biases1[8]))
41
-
    let ouput_layer10 = relu(calc(input, weight1[9], biases1[9]))
42
-
    let ouput_layer11 = relu(calc(input, weight1[10], biases1[10]))
43
-
    let ouput_layer12 = relu(calc(input, weight1[11], biases1[11]))
44
-
[ouput_layer1, ouput_layer2, ouput_layer3, ouput_layer4, ouput_layer5, ouput_layer6, ouput_layer7, ouput_layer8, ouput_layer9, ouput_layer10, ouput_layer11, ouput_layer12]
32
+
    let output_layer1 = relu(calc(input, weight1[0], biases1[0]))
33
+
    let output_layer2 = relu(calc(input, weight1[1], biases1[1]))
34
+
    let output_layer3 = relu(calc(input, weight1[2], biases1[2]))
35
+
    let output_layer4 = relu(calc(input, weight1[3], biases1[3]))
36
+
    let output_layer5 = relu(calc(input, weight1[4], biases1[4]))
37
+
    let output_layer6 = relu(calc(input, weight1[5], biases1[5]))
38
+
    let output_layer7 = relu(calc(input, weight1[6], biases1[6]))
39
+
    let output_layer8 = relu(calc(input, weight1[7], biases1[7]))
40
+
    let output_layer9 = relu(calc(input, weight1[8], biases1[8]))
41
+
    let output_layer10 = relu(calc(input, weight1[9], biases1[9]))
42
+
    let output_layer11 = relu(calc(input, weight1[10], biases1[10]))
43
+
    let output_layer12 = relu(calc(input, weight1[11], biases1[11]))
44
+
[output_layer1, output_layer2, output_layer3, output_layer4, output_layer5, output_layer6, output_layer7, output_layer8, output_layer9, output_layer10, output_layer11, output_layer12]
45
45
 
    }
46
46
 
47
47
 

Full: 
Old
New
Differences
1
1
 
{-# STDLIB_VERSION 6 #-}
2
2
 
{-# SCRIPT_TYPE ACCOUNT #-}
3
3
 
{-# CONTENT_TYPE DAPP #-}
4
4
 
let species = ["Iris-setosa", "Iris-versicolor", "Iris-virginica"]
5
5
 
6
6
 
let weight1 = [[6157, -3066, 12102, 17305], [-3936, -2569, -2816, 392], [6633, 300, 11435, 11685], [4149, -4959, -3121, 917], [6310, -9286, 8772, 266], [-527, 5610, -2987, -12595], [6988, -5565, 11513, 14717], [2688, 5935, -9544, -8824], [2346, 6692, -6381, -13268], [2916, 10874, -10078, -11116], [-3257, 18970, -13738, -18644], [10669, -7058, 16831, 17339]]
7
7
 
8
8
 
let biases1 = [-2287, -3248, -5442, -3810, 3699, 11759, -1281, 11270, 12675, 12008, 10765, -2116]
9
9
 
10
10
 
let weight2 = [[-14019, -170, -13032, 2440, -11741, 13771, -15437, 12736, 13684, 14834, 18289, -12514], [-787, 525, -5546, -28, 3778, 14674, 330, 15426, 13747, 10007, -21208, 465], [6177, 1093, 9648, 1825, 1335, -20733, 6854, -25641, -25315, -18382, -8672, 7714]]
11
11
 
12
12
 
let bias2 = [6583, 6472, -4596]
13
13
 
14
14
 
func relu (x) = if ((x > 0))
15
15
 
    then x
16
16
 
    else 0
17
17
 
18
18
 
19
19
 
func calc (input,weight,bias) = {
20
20
 
    let calc = (((((input[0] * weight[0]) + (input[1] * weight[1])) + (input[2] * weight[2])) + (input[3] * weight[3])) + bias)
21
21
 
    calc
22
22
 
    }
23
23
 
24
24
 
25
25
 
func calc_second_layer (input,weight,bias) = {
26
26
 
    let calc_second = (((((((((((((input[0] * weight[0]) + (input[1] * weight[1])) + (input[2] * weight[2])) + (input[3] * weight[3])) + (input[4] * weight[4])) + (input[5] * weight[5])) + (input[6] * weight[6])) + (input[7] * weight[7])) + (input[8] * weight[8])) + (input[9] * weight[9])) + (input[10] * weight[10])) + (input[11] * weight[11])) + bias)
27
27
 
    calc_second
28
28
 
    }
29
29
 
30
30
 
31
31
 
func calculateFirstLayer (input) = {
32
-
    let ouput_layer1 = relu(calc(input, weight1[0], biases1[0]))
33
-
    let ouput_layer2 = relu(calc(input, weight1[1], biases1[1]))
34
-
    let ouput_layer3 = relu(calc(input, weight1[2], biases1[2]))
35
-
    let ouput_layer4 = relu(calc(input, weight1[3], biases1[3]))
36
-
    let ouput_layer5 = relu(calc(input, weight1[4], biases1[4]))
37
-
    let ouput_layer6 = relu(calc(input, weight1[5], biases1[5]))
38
-
    let ouput_layer7 = relu(calc(input, weight1[6], biases1[6]))
39
-
    let ouput_layer8 = relu(calc(input, weight1[7], biases1[7]))
40
-
    let ouput_layer9 = relu(calc(input, weight1[8], biases1[8]))
41
-
    let ouput_layer10 = relu(calc(input, weight1[9], biases1[9]))
42
-
    let ouput_layer11 = relu(calc(input, weight1[10], biases1[10]))
43
-
    let ouput_layer12 = relu(calc(input, weight1[11], biases1[11]))
44
-
[ouput_layer1, ouput_layer2, ouput_layer3, ouput_layer4, ouput_layer5, ouput_layer6, ouput_layer7, ouput_layer8, ouput_layer9, ouput_layer10, ouput_layer11, ouput_layer12]
32
+
    let output_layer1 = relu(calc(input, weight1[0], biases1[0]))
33
+
    let output_layer2 = relu(calc(input, weight1[1], biases1[1]))
34
+
    let output_layer3 = relu(calc(input, weight1[2], biases1[2]))
35
+
    let output_layer4 = relu(calc(input, weight1[3], biases1[3]))
36
+
    let output_layer5 = relu(calc(input, weight1[4], biases1[4]))
37
+
    let output_layer6 = relu(calc(input, weight1[5], biases1[5]))
38
+
    let output_layer7 = relu(calc(input, weight1[6], biases1[6]))
39
+
    let output_layer8 = relu(calc(input, weight1[7], biases1[7]))
40
+
    let output_layer9 = relu(calc(input, weight1[8], biases1[8]))
41
+
    let output_layer10 = relu(calc(input, weight1[9], biases1[9]))
42
+
    let output_layer11 = relu(calc(input, weight1[10], biases1[10]))
43
+
    let output_layer12 = relu(calc(input, weight1[11], biases1[11]))
44
+
[output_layer1, output_layer2, output_layer3, output_layer4, output_layer5, output_layer6, output_layer7, output_layer8, output_layer9, output_layer10, output_layer11, output_layer12]
45
45
 
    }
46
46
 
47
47
 
48
48
 
func calculateSecondLayer (input) = {
49
49
 
    let output_layer1 = calc_second_layer(input, weight2[0], bias2[0])
50
50
 
    let output_layer2 = calc_second_layer(input, weight2[1], bias2[1])
51
51
 
    let output_layer3 = calc_second_layer(input, weight2[2], bias2[2])
52
52
 
[output_layer1, output_layer2, output_layer3]
53
53
 
    }
54
54
 
55
55
 
56
56
 
func forward_prop (input) = {
57
57
 
    let first_layer = calculateFirstLayer(input)
58
58
 
    let second_layer = calculateSecondLayer(first_layer)
59
59
 
    second_layer
60
60
 
    }
61
61
 
62
62
 
63
63
 
func find_pred (output) = {
64
64
 
    let max1 = if ((output[0] > output[1]))
65
65
 
        then 0
66
66
 
        else 1
67
67
 
    let max2 = if ((max1 > output[2]))
68
68
 
        then max1
69
69
 
        else 2
70
70
 
    max2
71
71
 
    }
72
72
 
73
73
 
74
74
 
@Callable(i)
75
75
 
func prediction (input) = {
76
76
 
    let output = forward_prop(input)
77
77
 
    let callerAddress = toString(i.caller)
78
78
 
    let pred = find_pred(output)
79
79
 
[IntegerEntry((callerAddress + "_1"), output[0]), IntegerEntry((callerAddress + "_2"), output[1]), IntegerEntry((callerAddress + "_3"), output[2]), StringEntry((callerAddress + "_p"), species[pred])]
80
80
 
    }
81
81
 
82
82
 

github/deemru/w8io/169f3d6 
39.28 ms ◑