70 lines
12 KiB
Plaintext
70 lines
12 KiB
Plaintext
|
Ë
|
|||
|
|
=û gÓ# ã óŽ — d dl Z d dlmZ d dlmZmZmZ d dlZd dlm Z m
|
|||
|
|
Z
|
|||
|
|
m Z m Z m
|
|||
|
|
Z
|
|||
|
|
d dlmZ d dlmZ d dlmZ dd lmZ dd
|
|||
|
|
lmZ dd lmZ d d
|
|||
|
|
lmZmZm Z m Z m Z m Z m Z e jB ddddœ¬« edddd¬« edd¬« edddd¬« edd d d ¬« edd d d!¬« edd"d#d$¬« edd%d&d'¬« edd(d)d*¬« edd+d,d-¬« edd.d/d0¬« edd1d2d3¬« ed4d5d6d7¬« f d8ejD d9ed:e#d;e#d<e$d=e$d>e$d?e$d@e$dAe$dBe$dCe$dDe%fdE„« Z&ddFœdGeee#ef fdH„Z'dI„ Z(dOdJe#fdK„Z)dL„ Z*dM„ Z+dN„ Z,y)Pé N)ÚPath)ÚAnyÚDictÚOptional)ÚModelÚdata_validationÚfix_random_seedÚset_dropout_rateÚset_gpu_allocator)Úmsg)ÚExample)Úresolve_dot_namesé )Úutil)ÚConfigSchemaTraining)Úregistryé )ÚArgÚOptÚ debug_cliÚparse_config_overridesÚ setup_gpuÚshow_validation_errorÚstring_to_listÚmodelT)Úallow_extra_argsÚignore_unknown_options)Úcontext_settings.zPath to config file)ÚhelpÚexistsÚ
|
|||
|
|
allow_dashzDName of the pipeline component of which the model should be analysed)r Ú z--layersz-lz+Comma-separated names of layer IDs to printFz --dimensionsz-DIMzShow dimensionsz --parametersz-PARzShow parametersz --gradientsz-GRADzShow gradientsz --attributesz-ATTRzShow attributesz
|
|||
|
|
--print-step0z-P0zPrint model before trainingz
|
|||
|
|
--print-step1z-P1z Print model after initializationz
|
|||
|
|
--print-step2z-P2zPrint model after trainingz
|
|||
|
|
--print-step3z-P3zPrint final predictionséÿÿÿÿz--gpu-idz-gzGPU ID or -1 for CPUÚctxÚ config_pathÚ componentÚlayersÚ
|
|||
|
|
dimensionsÚ
|
|||
|
|
parametersÚ gradientsÚ
|
|||
|
|
attributesÚP0ÚP1ÚP2ÚP3Úuse_gpuc
|
|||
|
|
|
|||
|
|
óª — t | « t |d¬« }||||||| |
|
|||
|
|
| dœ }
|
|||
|
|
t | j « }t |« 5 t j ||d¬« }ddd« j « }|d d }| d k\ r
|
|||
|
|
|r t |« t |« 5 t j |« }|j j « }t j |d t ¬
|
|||
|
|
« }ddd« d }|�#t j d |› �« t! |« j# |« }t% |||||
|
|||
|
|
¬
|
|||
|
|
« y# 1 sw Y ŒàxY w# 1 sw Y ŒaxY w)z«
|
|||
|
|
Analyze a Thinc model implementation. Includes checks for internal structure
|
|||
|
|
and activations during training.
|
|||
|
|
|
|||
|
|
DOCS: https://spacy.io/api/cli#debug-model
|
|||
|
|
T)Úintify) r( r) r* r+ r' Úprint_before_trainingÚprint_after_initÚprint_after_trainingÚprint_predictionF)Ú overridesÚ interpolateNÚtrainingÚ
|
|||
|
|
gpu_allocatorr )ÚschemaÚseedzFixing random seed: ©Úprint_settings)r r r Úargsr r Ú load_configr8 r Úload_model_from_configÚconfigr Úresolver r Úinfor Úget_pipeÚ debug_model)r$ r% r& r' r( r) r* r+ r, r- r. r/ r0 r> Úconfig_overridesÚ
|
|||
|
|
raw_configrB Ú allocatorÚnlpÚTr< Úpipes úVC:\Users\garci\AppData\Roaming\Python\Python312\site-packages\spacy/cli/debug_model.pyÚdebug_model_clirN sD € ô6 ˆgÔÜ
|
|||
|
|
˜F¨4Ô
|
|||
|
|
0€Fà Ø Ø Ø ØØ!#Ø Ø "Ø ñ
|
|||
|
|
€Nô .¨c¯h©hÓ7ÐÜ ˜{Õ +Ü×%Ñ%Ø Ð#3Àô
|
|||
|
|
ˆ
|
|||
|
|
÷
|
|||
|
|
,ð ×
|
|||
|
|
#Ñ
|
|||
|
|
#Ó
|
|||
|
|
%€FØ�zÑ" ?Ñ3€IØ�!‚|™ ܘ)Ô$Ü ˜{Õ +Ü×)Ñ)¨*Ó5ˆØ—‘×'Ñ'Ó)ˆÜ × Ñ ˜V JÑ /Ô8LÔ Mˆ÷
|
|||
|
|
,ð
|
|||
|
|
ˆV‰9€DØ ÐÜ �‰Ð'¨ vÐ.Ô/Ü˜Ô Ø �<‰<˜ Ó "€Dä�˜˜3 °^ÖD÷%
|
|||
|
|
,Ð +ú÷
|
|||
|
|
,Ð +ús ÁD=ÂAE Ä=EÅ Er= r> c
|
|||
|
|
ó¨ ‡‡ ‡
|
|||
|
|
— t |d« st j d|› d�d¬« |j }t |t
|
|||
|
|
« s$t j dt
|
|||
|
|
|« › d�d¬« |€i }t j d|j › �« |j d « r!t j d
|
|||
|
|
« t ||« t d « 5 |d g}t « 5 t | |« \ Š
|
|||
|
|
‰j ˆˆ
|
|||
|
|
fd
|
|||
|
|
„« d d d « t j d« t! t# j$ ‰
|
|||
|
|
‰« d« « Š d d d « |j d« r!t j d« t ||« t3 |d« d }|j5 d« r.d|j7 d« j8 v r‰j; d« }|j5 d« r.d|j7 d« j8 v r‰j; d« }t= d « D ]& } |r|j? ‰ « |j? ‰ « Œ( |j d « r!t j d « t ||« |jA ‰ D �
|
|||
|
|
cg c] }
|
|||
|
|
|
|
|||
|
|
jB ‘Œ c}
|
|||
|
|
« } |j d « r3t j d « t j tE | « « t jF d!« y # 1 sw Y �ŒóxY w# t& $ r´ t) d|¬« t « 5 t+ « D �cg c] }t- j. |i « ‘Œ nc c}w c}Š ‰j ˆ fd„« d d d « n # 1 sw Y nxY wt j d« n&# t0 $ r t j dd¬« Y nw xY wY �Œxw xY w# 1 sw Y �Œ~xY wc c}
|
|||
|
|
w )"Nr zThe component 'z0' does not specify an object that holds a Model.r )Úexitsz1Requires a Thinc Model to be analysed, but found z instead.zAnalysing model with ID r3 zSTEP 0 - before trainingFÚ train_corpusc ó •— ‰‰ « S ©N© )rJ rQ s €€rM ú<lambda>z debug_model.<locals>.<lambda>€ s
|
|||
|
|
ø€ ¡|°CÔ'8ó z/Initialized the model with the training corpus.é é )ÚnOr c ó •— ‰ S rS rT )Úexampless €rM rU z debug_model.<locals>.<lambda>ˆ s ø€ ©8rV z&Initialized the model with dummy data.zjCould not initialize the model: you'll have to provide a valid 'train_corpus' argument in the config file.r4 z STEP 1 - after initializationgš™™™™™É?Útok2vecztok2vec-listenerztransformer-listenerÚ transformeré r5 zSTEP 2 - after trainingr6 zSTEP 3 - predictionz.Succesfully ended analysis - model looks good.)$Úhasattrr Úfailr Ú
|
|||
|
|
isinstancer ÚtyperD ÚidÚgetÚdividerÚ _print_modelr r r Ú
|
|||
|
|
initializeÚlistÚ itertoolsÚisliceÚ
|
|||
|
|
ValueErrorÚ_set_output_dimÚ _get_docsr
|
|||
|
|
Ú from_dictÚ Exceptionr
|
|||
|
|
Úhas_refÚget_refÚnamerE ÚrangeÚupdateÚpredictÚ predictedÚstrÚgood)rB Úresolved_train_configrJ rL r> r Ú dot_namesÚxÚupstream_componentÚeÚexÚ
|
|||
|
|
predictionr[ rQ s ` @@rM rF rF ^ s ú€ ô �4˜Ô !Ü �‰Ø ˜d˜VÐ#SÐ TØõ
|
|||
|
|
ð
|
|||
|
|
�J‰J€EÜ �eœUÔ #Ü �‰Ø?ÄÀUà ¸}ÈIÐ VØõ
|
|||
|
|
ð Р؈ô ‡H�HÐ'¨¯© zÐ
|
|||
|
|
2Ô3Ø×ÑÐ1Ô2Ü � ‰ Ð.Ô0Ü�U˜NÔ+ô
|
|||
|
|
˜Õ ð Ø.¨~Ñ>Ð?ˆIÜ&Õ(Ü"3°F¸IÓ"F‘� Ø—‘Ô 8Ô9÷ )ô
|