U ʹjI @sddlZddlZddlZddlmZddlmZmZmZm Z m Z ddl m Z ddl mZddlmZmZddlmZddlmZdd lmZmZmZmZdd lmZdd lmZdd lm Z dd l!m"Z"e#e$Z%da&da'e(ej)*dddkZ+dddddddgZ,ddZ-d+ddZ.d,ddZ/d-e j0eeeedddZ1d.e j0eee(e(eee2d d!dZ3d"dZ4d#d$Z5d%d&Z6d/e7ed'd(dZ8d0ee7e2eeeeee eee2eeee e7d) d*dZ9dS)1N)deepcopy)OptionalDictCallableAnyTuple)nn)load_state_dict_from_url)FeatureListNetFeatureHookNet)FeatureGraphNet)load_state_dict) has_hf_hubdownload_cached_filecheck_cached_fileload_state_dict_from_hf)adapt_input_conv) PretrainedCfg)adapt_model_from_file)get_pretrained_cfgFZTIMM_USE_OLD_CACHE set_pretrained_download_progressset_pretrained_check_hashload_custom_pretrainedload_pretrainedpretrained_cfg_for_featuresresolve_pretrained_cfgbuild_model_with_cfgc Cs|dd}|dd}|dd}|dd}|dd}d}d}|dkrhtdd rhd}|sbt|}nj|rd}|}t|tstnN|rd}|}n@d }tr|rt|nd }|s|rtdd rd}|}n |rd}|}|dkr|d dr||d f}||fS) Nsourceurlfile state_dict hf_hub_idhf-hubT)Z necessaryFZhf_hub_filename)getrAssertionError isinstancedict_USE_OLD_CACHEr) pretrained_cfgZ cfg_sourceZpretrained_urlZpretrained_fileZ pretrained_sdr" load_frompretrained_locZold_cache_validr,S/var/www/html/bwave/python/venv/lib/python3.8/site-packages/timm/models/_builder.py_resolve_pretrained_sources<      r.TcCs|adS)zA Set download progress for pretrained weights on/off (globally). N)_DOWNLOAD_PROGRESSenabler,r,r-rLscCs|adS)z= Set hash checking for pretrained weights on/off (globally). N) _CHECK_HASHr0r,r,r-rRs)modelr)load_fncCs|pt|dd}|s"tddSt|\}}|s@tddS|dkrTtdn|dkrjt|ttd}|dk r~|||n t|d r||n td dS) aLoads a custom (read non .pth) weight file Downloads checkpoint file into cache-dir like torch.hub based loaders, but calls a passed in custom load fun, or the `load_pretrained` model member fn. If the object is already present in `model_dir`, it's deserialized and returned. The default value of `model_dir` is ``/checkpoints`` where `hub_dir` is the directory returned by :func:`~torch.hub.get_dir`. Args: model: The instantiated model to load weights into pretrained_cfg (dict): Default pretrained model cfg load_fn: An external standalone fn that loads weights into provided model, otherwise a fn named 'laod_pretrained' on the model will be called if it exists r)Nz/Invalid pretrained config, cannot load weights.zHNo pretrained weights exist for this model. Using random initialization.r#zKHugging Face hub not currently supported for custom load pretrained models.r) check_hashprogressrzXValid function to load pretrained weights is not available, using random initialization.) getattr_loggerwarningr.rr2r/hasattrr)r3r)r4r*r+r,r,r-rXs*       )r3r) num_classesin_chans filter_fnstrictc CsJ|pt|dd}|stdt|\}}|dkr@td|}n|dkr~td|d|d d rt||dSt|}n|d krtd |d|d d rt|t t d }||dSt |dt t d}n\|dkrtd|dt |t tfrt|}nt|}n|dd} td| d|dk rtz|||}Wn,tk rr} z ||}W5d} ~ XYnX|dd} | dk r*|dkr*t | tr| f} | D]~} | d} z.t||| || <td| d|dWn@tk r$} z || =d }td| dW5d} ~ XYnXq|dd}|dd }|dk rt |tr^|f}||d!kr|D]&}||dd||d"dqpd }nV|d kr|D]F}||d}||d||d<||d"}||d||d"<q|j||d#}|jr$td$d%|jd&|jrFtd'd%|jd(dS))a Load pretrained checkpoint Args: model (nn.Module) : PyTorch model module pretrained_cfg (Optional[Dict]): configuration for pretrained weights / target dataset num_classes (int): num_classes for target model in_chans (int): in_chans for target model filter_fn (Optional[Callable]): state_dict filter fn for load (takes state_dict, model as args) strict (bool): strict load of checkpoint r)NzWInvalid pretrained config, cannot load weights. Use `pretrained=False` for random init.r!z*Loading pretrained weights from state dictr z&Loading pretrained weights from file ()Z custom_loadFrz%Loading pretrained weights from url ()r6r5cpu)Z map_locationr6r5r#z2Loading pretrained weights from Hugging Face hub ( architecturez this modelz No pretrained weights exist for z). Use `pretrained=False` for random init.Z first_convr<z.weightzConverted input conv z pretrained weights from 3 to z channel(s)zUnable to convert pretrained z+ weights, using random init for this layer. classifier label_offsetrr=z.bias)r@zMissing keys (z, zZ) discovered while loading pretrained weights. This is expected if model is being adapted.zUnexpected keys (zY) found while loading pretrained weights. This may be expected if model is being adapted.)r7 RuntimeErrorr.r8infor$rr rr/r2r r&listtupler TypeErrorstrrNotImplementedErrorr9popZ missing_keysjoinZunexpected_keys)r3r)r=r>r?r@r*r+r!Z model_nameeZ input_convsZinput_conv_nameZ weight_name classifiersrEZclassifier_nameZclassifier_weightZclassifier_biasZ load_resultr,r,r-rs                      cCs&t|}d}|D]}||dq|S)N)r=rD global_pool)rrM)r)Z to_removetrr,r,r-rs cCs&|r|s dS|D]}||dqdS)N)rM)kwargsnamesnr,r,r-_filter_kwargssrVcCs d}|ddr|d7}|D]}|dkrb|dd}|dk rt|dksLt|||d dq|d kr|dd}|dk rt|dkst|||d q|d kr||d}|dk r|d kr||||q||d}|dk r||||qt||d dS)a& Update the default_cfg and kwargs before passing to model Args: pretrained_cfg: input pretrained cfg (updated in-place) kwargs: keyword args passed to model build fn (updated in-place) kwargs_filter: keyword arg keys that must be removed before model __init__ )r=rQr>Zfixed_input_sizeF)img_sizerW input_sizeNr<r>rr=)rT)r$lenr% setdefaultrV)r)rS kwargs_filterZdefault_kwarg_namesrUrXZ default_valr,r,r-_update_default_model_kwargss,      r])variantreturncCs|}d}|r4t|tr"tf|}nt|tr4|}d}|sR|rJd||g}t|}|sntd|dt}|pti}|js| d|t j |f|}|S)N.z*No pretrained configuration specified for ze model. Using a default. Please add a config to the model pretrained_cfg registry or pass explicitly.rC) r&r'rrKrNrr8r9rCr[ dataclassesreplace)r^r)pretrained_cfg_overlayZmodel_with_tagZpretrained_tagr,r,r-r1s,     ) model_clsr^ pretrainedr)rc model_cfg feature_cfgpretrained_strictpretrained_filter_fnr\c Ks| dd} d} |pi}t|||d}|}t|| | | ddrld} |ddd| krl| d|d<|dkr|f| } n|fd |i| } || _| j| _| rt| |} | rd nt| d | d d }|rt | ||| d d||d| rt }t| dd}|dk r|d|d|krr|d}t |t rr|}d|krNt}n$|dkr^t}ndsrtd||| f|} t|| _| j| _| S)a Build model with specified default_cfg and optional model_cfg This helper fn aids in the construction of a model including: * handling default_cfg and associated pretrained weight loading * passing through optional model_cfg for models with config based arch spec * features_only model adaptation * pruning config / model adaptation Args: model_cls (nn.Module): model class variant (str): model variant name pretrained (bool): load pretrained weights pretrained_cfg (dict): model's pretrained weight/task config model_cfg (Optional[Dict]): model's architecture config feature_cfg (Optional[Dict]: feature extraction adapter config pretrained_strict (bool): load pretrained weights strictly pretrained_filter_fn (Optional[Callable]): filter callable for pretrained weights kwargs_filter (Optional[Tuple]): kwargs to filter before passing to model **kwargs: model args passed through to model __init__ prunedF)r)rcZ features_onlyTZ out_indices)rr<Ncfgrr=r;r>r<)r)r=r>r?r@ output_fmt feature_clshookZfxzUnknown feature class )rMrto_dictr]r[r)Z default_cfgrr7r$rr r&rKlowerr r r%r)rdr^rer)rcrfrgrhrir\rSrjfeaturesr3Znum_classes_pretrainedrpror,r,r-rTsd!                  )T)T)NN)Nr;r<NT)NN)NNNNTNN):raloggingoscopyrtypingrrrrrZtorchrZ torch.hubr Ztimm.models._featuresr r Ztimm.models._features_fxr Ztimm.models._helpersr Ztimm.models._hubrrrrZtimm.models._manipulaterZtimm.models._pretrainedrZtimm.models._prunerZtimm.models._registryr getLogger__name__r8r/r2intenvironr$r(__all__r.rrModulerboolrrrVr]rKrrr,r,r,r-s          -   0 r + '