-
Notifications
You must be signed in to change notification settings - Fork 42
/
Copy pathmodels.html
190 lines (133 loc) · 10.3 KB
/
models.html
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
180
181
182
183
184
185
186
187
188
189
---
title: Adapters for SmilesTransformer models
keywords: fastai
sidebar: home_sidebar
summary: "Adapting SmilesTransformer models to use a SmilesTokenizer"
description: "Adapting SmilesTransformer models to use a SmilesTokenizer"
nb_path: "nbs/07_models.ipynb"
---
<!--
#################################################
### THIS FILE WAS AUTOGENERATED! DO NOT EDIT! ###
#################################################
# file to edit: nbs/07_models.ipynb
# command to build the docs after a change: nbdev_build_docs
-->
<div class="container" id="notebook-container">
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
</div>
{% endraw %}
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
</div>
{% endraw %}
<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="SmilesLanguageModelingModel">SmilesLanguageModelingModel<a class="anchor-link" href="#SmilesLanguageModelingModel"> </a></h2>
</div>
</div>
</div>
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_markdown rendered_html output_subarea ">
<h2 id="SmilesLanguageModelingModel" class="doc_header"><code>class</code> <code>SmilesLanguageModelingModel</code><a href="https://github.com/rxn4chemistry/rxnfp/tree/master/rxnfp/models.py#L46" class="source_link" style="float:right">[source]</a></h2><blockquote><p><code>SmilesLanguageModelingModel</code>(<strong><code>model_type</code></strong>, <strong><code>model_name</code></strong>, <strong><code>generator_name</code></strong>=<em><code>None</code></em>, <strong><code>discriminator_name</code></strong>=<em><code>None</code></em>, <strong><code>train_files</code></strong>=<em><code>None</code></em>, <strong><code>args</code></strong>=<em><code>None</code></em>, <strong><code>use_cuda</code></strong>=<em><code>True</code></em>, <strong><code>cuda_device</code></strong>=<em><code>-1</code></em>, <strong>**<code>kwargs</code></strong>) :: <code>LanguageModelingModel</code></p>
</blockquote>
</div>
</div>
</div>
</div>
</div>
{% endraw %}
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
</div>
{% endraw %}
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">default_vocab_path</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">pkg_resources</span><span class="o">.</span><span class="n">resource_filename</span><span class="p">(</span>
<span class="s2">"rxnfp"</span><span class="p">,</span>
<span class="s2">"models/transformers/bert_ft/vocab.txt"</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">SmilesLanguageModelingModel</span><span class="p">(</span><span class="n">model_type</span><span class="o">=</span><span class="s1">'bert'</span><span class="p">,</span> <span class="n">model_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">{</span><span class="s1">'vocab_path'</span><span class="p">:</span> <span class="n">default_vocab_path</span><span class="p">})</span>
</pre></div>
</div>
</div>
</div>
</div>
{% endraw %}
<div class="cell border-box-sizing text_cell rendered"><div class="inner_cell">
<div class="text_cell_render border-box-sizing rendered_html">
<h2 id="SmilesClassificationModel">SmilesClassificationModel<a class="anchor-link" href="#SmilesClassificationModel"> </a></h2>
</div>
</div>
</div>
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_markdown rendered_html output_subarea ">
<h2 id="SmilesClassificationModel" class="doc_header"><code>class</code> <code>SmilesClassificationModel</code><a href="https://github.com/rxn4chemistry/rxnfp/tree/master/rxnfp/models.py#L297" class="source_link" style="float:right">[source]</a></h2><blockquote><p><code>SmilesClassificationModel</code>(<strong><code>model_type</code></strong>, <strong><code>model_name</code></strong>, <strong><code>tokenizer_type</code></strong>=<em><code>None</code></em>, <strong><code>tokenizer_name</code></strong>=<em><code>None</code></em>, <strong><code>num_labels</code></strong>=<em><code>None</code></em>, <strong><code>weight</code></strong>=<em><code>None</code></em>, <strong><code>args</code></strong>=<em><code>None</code></em>, <strong><code>use_cuda</code></strong>=<em><code>True</code></em>, <strong><code>cuda_device</code></strong>=<em><code>-1</code></em>, <strong><code>onnx_execution_provider</code></strong>=<em><code>None</code></em>, <strong><code>freeze_encoder</code></strong>=<em><code>False</code></em>, <strong><code>freeze_all_but_one</code></strong>=<em><code>False</code></em>, <strong>**<code>kwargs</code></strong>) :: <code>ClassificationModel</code></p>
</blockquote>
</div>
</div>
</div>
</div>
</div>
{% endraw %}
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
</div>
{% endraw %}
{% raw %}
<div class="cell border-box-sizing code_cell rendered">
<div class="input">
<div class="inner_cell">
<div class="input_area">
<div class=" highlight hl-ipython3"><pre><span></span><span class="n">default_model_path</span> <span class="o">=</span> <span class="p">(</span>
<span class="n">pkg_resources</span><span class="o">.</span><span class="n">resource_filename</span><span class="p">(</span>
<span class="s2">"rxnfp"</span><span class="p">,</span>
<span class="s2">"models/transformers/bert_pretrained"</span>
<span class="p">)</span>
<span class="p">)</span>
<span class="n">model_args</span> <span class="o">=</span> <span class="p">{</span>
<span class="s1">'num_train_epochs'</span><span class="p">:</span> <span class="mi">10</span><span class="p">,</span> <span class="s1">'overwrite_output_dir'</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span>
<span class="s1">'learning_rate'</span><span class="p">:</span> <span class="mf">0.0001</span><span class="p">,</span> <span class="s1">'gradient_accumulation_steps'</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span>
<span class="s1">'regression'</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span> <span class="s2">"num_labels"</span><span class="p">:</span><span class="mi">1</span><span class="p">,</span> <span class="s2">"fp16"</span><span class="p">:</span> <span class="kc">False</span><span class="p">,</span>
<span class="s2">"evaluate_during_training"</span><span class="p">:</span> <span class="kc">True</span><span class="p">,</span> <span class="s1">'manual_seed'</span><span class="p">:</span> <span class="mi">42</span><span class="p">,</span>
<span class="s2">"max_seq_length"</span><span class="p">:</span> <span class="mi">300</span><span class="p">,</span> <span class="s2">"train_batch_size"</span><span class="p">:</span> <span class="mi">16</span><span class="p">,</span><span class="s2">"warmup_ratio"</span><span class="p">:</span> <span class="mf">0.00</span><span class="p">,</span>
<span class="s2">"config"</span> <span class="p">:</span> <span class="p">{</span> <span class="s1">'hidden_dropout_prob'</span><span class="p">:</span> <span class="mf">0.05</span> <span class="p">},</span>
<span class="c1"># 'wandb_project': 'test_project', </span>
<span class="p">}</span>
<span class="n">model</span> <span class="o">=</span> <span class="n">SmilesClassificationModel</span><span class="p">(</span><span class="s2">"bert"</span><span class="p">,</span> <span class="n">default_model_path</span><span class="p">,</span> <span class="n">num_labels</span><span class="o">=</span><span class="mi">5</span><span class="p">,</span>
<span class="n">args</span><span class="o">=</span><span class="n">model_args</span><span class="p">,</span> <span class="n">use_cuda</span><span class="o">=</span><span class="n">torch</span><span class="o">.</span><span class="n">cuda</span><span class="o">.</span><span class="n">is_available</span><span class="p">())</span>
</pre></div>
</div>
</div>
</div>
<div class="output_wrapper">
<div class="output">
<div class="output_area">
<div class="output_subarea output_stream output_stderr output_text">
<pre>Some weights of the model checkpoint at /home/phs/git/post/update/rxnfp/rxnfp/models/transformers/bert_pretrained were not used when initializing BertForSequenceClassification: ['cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.seq_relationship.bias']
- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at /home/phs/git/post/update/rxnfp/rxnfp/models/transformers/bert_pretrained and are newly initialized: ['classifier.weight', 'classifier.bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
</pre>
</div>
</div>
</div>
</div>
</div>
{% endraw %}
</div>