From 2146faffee949e1cac931c4bfd818d575d9eab69 Mon Sep 17 00:00:00 2001 From: Avadh Patel Date: Wed, 17 Jan 2018 06:04:22 -0600 Subject: [PATCH 1/5] Do not train model if its going to be loaded from disk This saves significant time in loading a model from disk. Signed-off-by: Avadh Patel --- spacy/syntax/nn_parser.pyx | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx index 28ffbb33f..7a722ae36 100644 --- a/spacy/syntax/nn_parser.pyx +++ b/spacy/syntax/nn_parser.pyx @@ -261,7 +261,8 @@ cdef class Parser: # TODO: This is an unfortunate hack atm! # Used to set input dimensions in network. - lower.begin_training(lower.ops.allocate((500, token_vector_width))) + if not cfg.get('from_disk', False): + lower.begin_training(lower.ops.allocate((500, token_vector_width))) cfg = { 'nr_class': nr_class, 'hidden_depth': depth, @@ -864,7 +865,7 @@ cdef class Parser: path = util.ensure_path(path) if self.model is True: self.cfg['pretrained_dims'] = self.vocab.vectors_length - self.model, cfg = self.Model(**self.cfg) + self.model, cfg = self.Model(from_disk=True, **self.cfg) else: cfg = {} with (path / 'tok2vec_model').open('rb') as file_: From fe879da2a1b1faa3d008b834a647d691e35bbac4 Mon Sep 17 00:00:00 2001 From: Avadh Patel Date: Wed, 17 Jan 2018 06:16:07 -0600 Subject: [PATCH 2/5] Do not train model if its going to be loaded from disk This saves significant time in loading a model from disk. Signed-off-by: Avadh Patel --- spacy/syntax/nn_parser.pyx | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx index bb01cecf1..12cb27bb2 100644 --- a/spacy/syntax/nn_parser.pyx +++ b/spacy/syntax/nn_parser.pyx @@ -271,7 +271,8 @@ cdef class Parser: # TODO: This is an unfortunate hack atm! # Used to set input dimensions in network. - lower.begin_training(lower.ops.allocate((500, token_vector_width))) + if not cfg.get('from_disk', False): + lower.begin_training(lower.ops.allocate((500, token_vector_width))) cfg = { 'nr_class': nr_class, 'hidden_depth': depth, @@ -888,7 +889,7 @@ cdef class Parser: path = util.ensure_path(path) if self.model is True: self.cfg['pretrained_dims'] = self.vocab.vectors_length - self.model, cfg = self.Model(**self.cfg) + self.model, cfg = self.Model(from_disk=True, **self.cfg) else: cfg = {} with (path / 'tok2vec_model').open('rb') as file_: From 5029d6573884047fd3cd1ba8ac581f13957acbf8 Mon Sep 17 00:00:00 2001 From: Avadh Patel Date: Wed, 17 Jan 2018 06:33:37 -0600 Subject: [PATCH 3/5] Signed contributor agreement Signed-off-by: Avadh Patel --- .github/contributors/avadhpatel.md | 106 +++++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/avadhpatel.md diff --git a/.github/contributors/avadhpatel.md b/.github/contributors/avadhpatel.md new file mode 100644 index 000000000..6609c7d5c --- /dev/null +++ b/.github/contributors/avadhpatel.md @@ -0,0 +1,106 @@ +# spaCy contributor agreement + +This spaCy Contributor Agreement (**"SCA"**) is based on the +[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf). +The SCA applies to any contribution that you make to any product or project +managed by us (the **"project"**), and sets out the intellectual property rights +you grant to us in the contributed materials. The term **"us"** shall mean +[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term +**"you"** shall mean the person or entity identified below. + +If you agree to be bound by these terms, fill in the information requested +below and include the filled-in version with your first pull request, under the +folder [`.github/contributors/`](/.github/contributors/). The name of the file +should be your GitHub username, with the extension `.md`. For example, the user +example_user would create the file `.github/contributors/example_user.md`. + +Read this agreement carefully before signing. These terms and conditions +constitute a binding legal agreement. + +## Contributor Agreement + +1. The term "contribution" or "contributed materials" means any source code, +object code, patch, tool, sample, graphic, specification, manual, +documentation, or any other material posted or submitted by you to the project. + +2. With respect to any worldwide copyrights, or copyright applications and +registrations, in your contribution: + + * you hereby assign to us joint ownership, and to the extent that such + assignment is or becomes invalid, ineffective or unenforceable, you hereby + grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge, + royalty-free, unrestricted license to exercise all rights under those + copyrights. This includes, at our option, the right to sublicense these same + rights to third parties through multiple levels of sublicensees or other + licensing arrangements; + + * you agree that each of us can do all things in relation to your + contribution as if each of us were the sole owners, and if one of us makes + a derivative work of your contribution, the one who makes the derivative + work (or has it made will be the sole owner of that derivative work; + + * you agree that you will not assert any moral rights in your contribution + against us, our licensees or transferees; + + * you agree that we may register a copyright in your contribution and + exercise all ownership rights associated with it; and + + * you agree that neither of us has any duty to consult with, obtain the + consent of, pay or render an accounting to the other for any use or + distribution of your contribution. + +3. With respect to any patents you own, or that you can license without payment +to any third party, you hereby grant to us a perpetual, irrevocable, +non-exclusive, worldwide, no-charge, royalty-free license to: + + * make, have made, use, sell, offer to sell, import, and otherwise transfer + your contribution in whole or in part, alone or in combination with or + included in any product, work or materials arising out of the project to + which your contribution was submitted, and + + * at our option, to sublicense these same rights to third parties through + multiple levels of sublicensees or other licensing arrangements. + +4. Except as set out above, you keep all right, title, and interest in your +contribution. The rights that you grant to us under these terms are effective +on the date you first submitted a contribution to us, even if your submission +took place before the date you sign these terms. + +5. You covenant, represent, warrant and agree that: + + * Each contribution that you submit is and shall be an original work of + authorship and you can legally grant the rights set out in this SCA; + + * to the best of your knowledge, each contribution will not violate any + third party's copyrights, trademarks, patents, or other intellectual + property rights; and + + * each contribution shall be in compliance with U.S. export control laws and + other applicable export and import laws. You agree to notify us if you + become aware of any circumstance which would make any of the foregoing + representations inaccurate in any respect. We may publicly disclose your + participation in the project, including the fact that you have signed the SCA. + +6. This SCA is governed by the laws of the State of California and applicable +U.S. Federal law. Any choice of law rules will not apply. + +7. Please place an “x” on one of the applicable statement below. Please do NOT +mark both statements: + + * [x] I am signing on behalf of myself as an individual and no other person + or entity, including my employer, has or will have rights with respect to my + contributions. + + * [ ] I am signing on behalf of my employer or a legal entity and I have the + actual authority to contractually bind that entity. + +## Contributor Details + +| Field | Entry | +|------------------------------- | -------------------- | +| Name | Avadh Patel | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | 17.01.2018 | +| GitHub username | avadhpatel | +| Website (optional) | | From 75903949da06130d85afc1d35bd1f6d2758adb9f Mon Sep 17 00:00:00 2001 From: Avadh Patel Date: Thu, 18 Jan 2018 06:51:57 -0600 Subject: [PATCH 4/5] Updated model building after suggestion from Matthew Signed-off-by: Avadh Patel --- spacy/syntax/nn_parser.pyx | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx index 7a722ae36..40485d45d 100644 --- a/spacy/syntax/nn_parser.pyx +++ b/spacy/syntax/nn_parser.pyx @@ -259,10 +259,6 @@ cdef class Parser: zero_init(Affine(nr_class, hidden_width, drop_factor=0.0)) ) - # TODO: This is an unfortunate hack atm! - # Used to set input dimensions in network. - if not cfg.get('from_disk', False): - lower.begin_training(lower.ops.allocate((500, token_vector_width))) cfg = { 'nr_class': nr_class, 'hidden_depth': depth, @@ -812,6 +808,8 @@ cdef class Parser: self.model, cfg = self.Model(self.moves.n_moves, **cfg) if sgd is None: sgd = self.create_optimizer() + self.model[1].begin_training( + self.model[1].ops.allocate((5, cfg['token_vector_width']))) self.init_multitask_objectives(gold_tuples, pipeline, sgd=sgd, **cfg) link_vectors_to_models(self.vocab) self.cfg.update(cfg) @@ -865,7 +863,7 @@ cdef class Parser: path = util.ensure_path(path) if self.model is True: self.cfg['pretrained_dims'] = self.vocab.vectors_length - self.model, cfg = self.Model(from_disk=True, **self.cfg) + self.model, cfg = self.Model(**self.cfg) else: cfg = {} with (path / 'tok2vec_model').open('rb') as file_: From a517df55c8d2a00fe9e9ece35763ad586e1caa13 Mon Sep 17 00:00:00 2001 From: Avadh Patel Date: Sun, 21 Jan 2018 15:20:45 -0600 Subject: [PATCH 5/5] Small fix Signed-off-by: Avadh Patel --- spacy/syntax/nn_parser.pyx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx index f8a3bb30e..a1563e03e 100644 --- a/spacy/syntax/nn_parser.pyx +++ b/spacy/syntax/nn_parser.pyx @@ -887,7 +887,7 @@ cdef class Parser: path = util.ensure_path(path) if self.model is True: self.cfg['pretrained_dims'] = self.vocab.vectors_length - self.model, cfg = self.Model(from_disk=True, **self.cfg) + self.model, cfg = self.Model(**self.cfg) else: cfg = {} with (path / 'tok2vec_model').open('rb') as file_: