-
Notifications
You must be signed in to change notification settings - Fork 268
/
learner.py
179 lines (161 loc) · 5.75 KB
/
learner.py
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
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
from .. import utils as U
from ..core import GenLearner
from ..imports import *
class NodeClassLearner(GenLearner):
"""
```
Main class used to tune and train Keras models for node classification
Main parameters are:
model (Model): A compiled instance of keras.engine.training.Model
train_data (Iterator): a Iterator instance for training set
val_data (Iterator): A Iterator instance for validation set
```
"""
def __init__(
self,
model,
train_data=None,
val_data=None,
batch_size=U.DEFAULT_BS,
eval_batch_size=U.DEFAULT_BS,
workers=1,
use_multiprocessing=False,
):
super().__init__(
model,
train_data=train_data,
val_data=val_data,
batch_size=batch_size,
eval_batch_size=eval_batch_size,
workers=workers,
use_multiprocessing=use_multiprocessing,
)
return
def view_top_losses(self, n=4, preproc=None, val_data=None):
"""
```
Views observations with top losses in validation set.
Typically over-ridden by Learner subclasses.
Args:
n(int or tuple): a range to select in form of int or tuple
e.g., n=8 is treated as n=(0,8)
preproc (Preprocessor): A TextPreprocessor or ImagePreprocessor.
For some data like text data, a preprocessor
is required to undo the pre-processing
to correctly view raw data.
val_data: optional val_data to use instead of self.val_data
Returns:
list of n tuples where first element is either
filepath or id of validation example and second element
is loss.
```
"""
val = self._check_val(val_data)
# get top losses and associated data
tups = self.top_losses(n=n, val_data=val, preproc=preproc)
# get multilabel status and class names
classes = preproc.get_classes() if preproc is not None else None
# iterate through losses
for tup in tups:
# get data
idx = tup[0]
loss = tup[1]
truth = tup[2]
pred = tup[3]
print("----------")
print(
"id:%s | loss:%s | true:%s | pred:%s)\n"
% (idx, round(loss, 2), truth, pred)
)
# print(obs)
return
def layer_output(self, layer_id, example_id=0, batch_id=0, use_val=False):
"""
```
Prints output of layer with index <layer_id> to help debug models.
Uses first example (example_id=0) from training set, by default.
```
"""
raise Exception(
"currently_unsupported: layer_output method is not yet supported for "
+ "graph neural networks in ktrain"
)
class LinkPredLearner(GenLearner):
"""
```
Main class used to tune and train Keras models for link prediction
Main parameters are:
model (Model): A compiled instance of keras.engine.training.Model
train_data (Iterator): a Iterator instance for training set
val_data (Iterator): A Iterator instance for validation set
```
"""
def __init__(
self,
model,
train_data=None,
val_data=None,
batch_size=U.DEFAULT_BS,
eval_batch_size=U.DEFAULT_BS,
workers=1,
use_multiprocessing=False,
):
super().__init__(
model,
train_data=train_data,
val_data=val_data,
batch_size=batch_size,
eval_batch_size=eval_batch_size,
workers=workers,
use_multiprocessing=use_multiprocessing,
)
return
def view_top_losses(self, n=4, preproc=None, val_data=None):
"""
```
Views observations with top losses in validation set.
Typically over-ridden by Learner subclasses.
Args:
n(int or tuple): a range to select in form of int or tuple
e.g., n=8 is treated as n=(0,8)
preproc (Preprocessor): A TextPreprocessor or ImagePreprocessor.
For some data like text data, a preprocessor
is required to undo the pre-processing
to correctly view raw data.
val_data: optional val_data to use instead of self.val_data
Returns:
list of n tuples where first element is either
filepath or id of validation example and second element
is loss.
```
"""
val = self._check_val(val_data)
# get top losses and associated data
tups = self.top_losses(n=n, val_data=val, preproc=preproc)
# get multilabel status and class names
classes = preproc.get_classes() if preproc is not None else None
# iterate through losses
for tup in tups:
# get data
idx = tup[0]
loss = tup[1]
truth = tup[2]
pred = tup[3]
print("----------")
print(
"id:%s | loss:%s | true:%s | pred:%s)\n"
% (idx, round(loss, 2), truth, pred)
)
# print(obs)
return
def layer_output(self, layer_id, example_id=0, batch_id=0, use_val=False):
"""
```
Prints output of layer with index <layer_id> to help debug models.
Uses first example (example_id=0) from training set, by default.
```
"""
raise Exception(
"currently_unsupported: layer_output method is not yet supported for "
+ "graph neural networks in ktrain"
)