# textcat.teach with custom model from spaCy **URL:** \ **Category:** Uncategorized\ **Tags:** textcat, spacy, solved\ **Created:** [May 19, 2020, 8:22pm UTC](https://support.prodi.gy/t/textcat-teach-with-custom-model-from-spacy/2928 "2020-05-19T20:22:32Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![HSM](https://avatars.discourse-cdn.com/v4/letter/h/ea666f/32.png) [@HSM](https://support.prodi.gy/u/HSM)\ **Post date:** [May 19, 2020, 8:22pm UTC](https://support.prodi.gy/t/textcat-teach-with-custom-model-from-spacy/2928/1 "2020-05-19T20:22:33Z")
Hi, I have trained a custom textcat model in spaCy and wanted to use that model as a base model to label more data in Prodigy but got this error. > ``` > Task queue depth is 1 > Exception when serving /get_questions > Traceback (most recent call last): > File "/opt/anaconda3/lib/python3.7/site-packages/waitress/channel.py", line 336, in service > task.service() > File "/opt/anaconda3/lib/python3.7/site-packages/waitress/task.py", line 175, in service > self.execute() > File "/opt/anaconda3/lib/python3.7/site-packages/waitress/task.py", line 452, in execute > app_iter = self.channel.server.application(env, start_response) > File "/opt/anaconda3/lib/python3.7/site-packages/hug/api.py", line 451, in api_auto_instantiate > return module. __hug_wsgi__ (*args, **kwargs) > File "/opt/anaconda3/lib/python3.7/site-packages/falcon/api.py", line 244, in __call__ > responder(req, resp, **params) > File "/opt/anaconda3/lib/python3.7/site-packages/hug/interface.py", line 789, in __call__ > raise exception > File "/opt/anaconda3/lib/python3.7/site-packages/hug/interface.py", line 762, in __call__ > self.render_content(self.call_function(input_parameters), context, request, response, **kwargs) > File "/opt/anaconda3/lib/python3.7/site-packages/hug/interface.py", line 698, in call_function > return self.interface(**parameters) > File "/opt/anaconda3/lib/python3.7/site-packages/hug/interface.py", line 100, in __call__ > return __hug_internal_self._function(*args, **kwargs) > File "/opt/anaconda3/lib/python3.7/site-packages/prodigy/_api/hug_app.py", line 206, in get_questions > tasks = controller.get_questions() > File "cython_src/prodigy/core.pyx", line 130, in prodigy.core.Controller.get_questions > File "cython_src/prodigy/components/feeds.pyx", line 58, in prodigy.components.feeds.SharedFeed.get_questions > File "cython_src/prodigy/components/feeds.pyx", line 63, in prodigy.components.feeds.SharedFeed.get_next_batch > File "cython_src/prodigy/components/feeds.pyx", line 140, in prodigy.components.feeds.SessionFeed.get_session_stream > File "/opt/anaconda3/lib/python3.7/site-packages/toolz/itertoolz.py", line 376, in first > return next(iter(seq)) > File "cython_src/prodigy/components/sorters.pyx", line 151, in __iter__ > File "cython_src/prodigy/components/sorters.pyx", line 61, in genexpr > File "cython_src/prodigy/util.pyx", line 381, in predict > File "/opt/anaconda3/lib/python3.7/site-packages/toolz/itertoolz.py", line 242, in interleave > yield next(itr) > File "cython_src/prodigy/models/textcat.pyx", line 168, in __call__ > File "/opt/anaconda3/lib/python3.7/site-packages/spacy/language.py", line 688, in pipe > for doc, context in izip(docs, contexts): > File "/opt/anaconda3/lib/python3.7/site-packages/spacy/language.py", line 716, in pipe > for doc in docs: > File "/opt/anaconda3/lib/python3.7/site-packages/spacy/language.py", line 903, in _pipe > for doc in docs: > File "pipes.pyx", line 914, in pipe > File "pipes.pyx", line 920, in spacy.pipeline.pipes.TextCategorizer.predict > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/neural/_classes/model.py", line 169, in __call__ > return self.predict(x) > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/neural/_classes/feed_forward.py", line 40, in predict > X = layer(X) > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/neural/_classes/model.py", line 169, in __call__ > return self.predict(x) > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/neural/_classes/model.py", line 133, in predict > y, _ = self.begin_update(X, drop=None) > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/api.py", line 163, in begin_update > values = [fwd(X, *a, **k) for fwd in forward] > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/api.py", line 163, in > values = [fwd(X, *a, **k) for fwd in forward] > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/api.py", line 256, in wrap > output = func(*args, **kwargs) > File "/opt/anaconda3/lib/python3.7/site-packages/thinc/neural/_classes/feed_forward.py", line 46, in begin_update > X, inc_layer_grad = layer.begin_update(X, drop=drop) > File "/opt/anaconda3/lib/python3.7/site-packages/spacy/_ml.py", line 679, in concatenate_lists_fwd > drop *= drop_factor > TypeError: unsupported operand type(s) for *=: 'NoneType' and 'float' > > ``` spaCy version 2.2.4 Prodigy Version 1.8.5 Command I used: > prodigy textcat.teach my\_dataset ./models/custom ./prodigy\_input.jsonl --label A,B,C --patterns ./patterns.jsonl ---
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [May 20, 2020, 12:21pm UTC](https://support.prodi.gy/t/textcat-teach-with-custom-model-from-spacy/2928/2 "2020-05-20T12:21:40Z")
Hi! What's in your `prodigy_input.jsonl` and where does the data come from? From the error, it sounds like something is being passed through that's `None` and shouldn't be. Does your data have anything pre-defined, like `"score"`? Or is anything else `None`/`null` or looks suspicious? ---
**Author:** ![HSM](https://avatars.discourse-cdn.com/v4/letter/h/ea666f/32.png) [@HSM](https://support.prodi.gy/u/HSM)\ **Post date:** [May 20, 2020, 1:44pm UTC](https://support.prodi.gy/t/textcat-teach-with-custom-model-from-spacy/2928/3 "2020-05-20T13:44:54Z")
I don't get any error while passing `en_vectors_web_lg` or `en_core_web_lg` as a base model. I tried with a simple txt file, and get the same error. And that jsonl file has nothing just dictionaries and `"text"` as a key. Also, my Prodigy uses Spacy 2.1 while i trained my custom model with 2.2 version. Could it be a problem here? ---
**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\ **Post date:** [May 21, 2020, 5:50pm UTC](https://support.prodi.gy/t/textcat-teach-with-custom-model-from-spacy/2928/4 "2020-05-21T17:50:39Z")
> [@HSM](#): > > Also, my Prodigy uses Spacy 2.1 while i trained my custom model with 2.2 version. Could it be a problem here? Ah, yes, that's most likely the problem then. Models are compatible between patch updates, but minor version updates require new models / retraining your models.