Blame view

LDA/04c-sae.py 2.88 KB
b6d0165d1   Killian   Initial commit
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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
  
  # coding: utf-8
  
  # In[2]:
  
  # Import
  import gensim
  from scipy import sparse
  import itertools
  from sklearn import preprocessing
  from keras.models import Sequential
  from keras.optimizers import SGD,Adam
  from mlp import *
  import mlp
  import sklearn.metrics
  import shelve
  import pickle
  from utils import *
  import sys
  import os
  import json
  # In[4]:
  
  sparse_model=shelve.open("{}".format(sys.argv[2]))
  in_dir = sys.argv[1]
  infer_model=shelve.open("{}/infer.shelve".format(in_dir))
  #['ASR', 'TRS', 'LABEL']
  # In[6]:
  ASR=sparse_model["ASR_wid"]
  TRS=sparse_model["TRS_wid"]
  LABEL=sparse_model["LABEL"]
  
  
  hidden_size=[40, 35 , 40 ,30 ]
  input_activation="tanh"
  out_activation="tanh"
  loss="mse"
  epochs=500
  batch=1
  patience=60
  do_do=False
  sgd = Adam(lr=0.00001)#SGD(lr=0.00001,nesterov=False) #'rmsprop'# Adam(lr=0.00001)#SGD(lr=0.001, momentum=0.9, nesterov=True)
  try :
      sgd_repr=sgd.get_config()["name"]
  except AttributeError :
      sgd_repr=sgd
  
  params={ "h1" : "_".join([str(x) for x in hidden_size]),
  	"inside_activation" : input_activation,
  	"out_activation" : out_activation,
          "do_dropout": do_do,
  	"loss" : loss,
  	"epochs" : epochs ,
  	"batch_size" : batch,
  	"patience" : patience,
          "sgd" : sgd_repr}
  name = "_".join([ str(x) for x in params.values()])
  try:
      os.mkdir("{}/{}".format(in_dir,name))
  except:
      pass
  db = shelve.open("{}/{}/ae_model.shelve".format(in_dir,name),writeback=True)
  #
  json.dump(params,
  	open("{}/{}/ae_model.json".format(in_dir,name),"w"),
  	indent=4)
  
  keys = ["ASR","TRS"]
  
  mlp_h = [ 40 , 35 , 40]
  mlp_loss ="categorical_crossentropy"
  mlp_dropouts = [0,0,0,0]
  mlp_sgd = Adam(0.0001)
  mlp_epochs = 200
  mlp_batch_size = 8
  
  db["SAE"] = {}
  for mod in keys : 
      res=train_ae(infer_model["LDA"][mod]["TRAIN"],infer_model["LDA"][mod]["DEV"],infer_model["LDA"][mod]["TEST"],hidden_size,patience = params["patience"],sgd=sgd,in_activation="tanh",out_activation="tanh",loss=loss,epochs=epochs,batch_size=batch,verbose=0)
      mlp_res_list=[]
      for layer in res :
          mlp_res_list.append(train_mlp(layer[0],LABEL["TRAIN"],layer[1],LABEL["DEV"],layer[2],LABEL["TEST"],mlp_h,loss=mlp_loss,dropouts=mlp_dropouts,sgd=mlp_sgd,epochs=mlp_epochs,batch_size=mlp_batch_size,fit_verbose=0))
      db["SAE"][mod]=mlp_res_list
  
  mod = "ASR"
  mod2= "TRS"
  mlp_res_list=[]
  
  res = train_ae(infer_model["LDA"][mod]["TRAIN"],infer_model["LDA"][mod]["DEV"],infer_model["LDA"][mod]["TEST"],hidden_size,dropouts=[0],patience = params["patience"],sgd=sgd,in_activation="tanh",out_activation="tanh",loss=loss,epochs=epochs,batch_size=batch,y_train=infer_model["LDA"][mod]["TRAIN"],y_dev=infer_model["LDA"][mod2]["DEV"],y_test=infer_model["LDA"][mod2]["TEST"])
  for layer in res :
      mlp_res_list.append(train_mlp(layer[0],LABEL["TRAIN"],layer[1],LABEL["DEV"],layer[2],LABEL["TEST"],mlp_h,loss=mlp_loss,dropouts=mlp_dropouts,sgd=mlp_sgd,epochs=mlp_epochs,batch_size=mlp_batch_size,fit_verbose=0))
  
  db["SAE"]["SPE"] = mlp_res_list
  
  
  db.close()