MatchingNetworks4XC/MNXC.config at support_w2v · SamujjwalSam/MatchingNetworks4XC · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
{
    "data" : {
        "dataset_name" : "Wiki10-31K",
        "val_split" : 0.2,
        "test_split" : 0.3
    },

    "xc_datasets" : {
        "AmazonCat-14K"    : "json",
        "Amazon-3M"        : "json",
        "Delicious-T140"   : "html",
        "Wiki10-31K"       : "html",
        "Wiki10-31K_onehot": "html",
        "Wiki10-31K_fixed5": "html",
        "AmazonCat-13K"    : "txt",
        "Amazon-670K"      : "txt",
        "EurLex"           : "uniq"
    },

    "model" : {
        "num_folds" : 5,
        "max_nb_words" : 20000,
        "max_sequence_length" : 100,
        "learning_rate" : 1,
        "lr_decay" : 1e-6,
        "weight_decay" : 1e-4,
        "optim" : "adam",
        "dropout" : 0.2,
        "clipnorm" : 3.0,
        "data_slice" : 5120,

        "g_encoder" : "cnn",
        "vectorizer": "doc2vec",
        "use_cuda" : 0,
        "sents_chunk_mode" : "word_sum",
        "normalize_inputs" : "false",
        "sample_repeat_mode" : "append",
        "tfidf_avg" : 0,
        "dropout_external" : 0,
        "kernel_size" : 1,
        "stride" : 1,
        "padding" : 1,
        "min_word_count" : 1,
        "context" : 10,
        "fce" : 0,

        "hid_size" : 64,
        "input_size" : 300,

        "num_epochs" : 30,
        "num_train_epoch" : 20,
        "batch_size" : 32,
        "categories_per_batch" : 5,
        "supports_per_category" : 4,
        "targets_per_category" : 4
    },

    "prep_vecs" : {
        "window" : 7,
        "negative" : 10,
        "num_chunks" : 10,
        "sents_chunk_mode" : "word_avg"
    },

    "paths" : {
        "result_file" : "result.txt",
        "log_dir" : "/logs",

        "pretrain_dir" : {
            "Windows" : "D:\\Datasets\\Extreme Classification",
            "Linux" : "/raid/ravi/pretrain",
            "OSX" : "/home/cs16resch01001/datasets/Extreme Classification"
        },

        "dataset_dir" : {
            "Windows" : "D:\\Datasets\\Extreme Classification",
            "Linux" : "/home/cs16resch01001/datasets/Extreme Classification",
            "OSX" : "/home/cs16resch01001/datasets/Extreme Classification"
        }
    }
}