o ZhsP @shddlZddlZddlmZmZmZddlZddlmm m m Z ddl mm m Zddlm Z ddlmZmZddlmZddlmZddlmZddlmZdd lmZmZejj ZGd d d ej Z!d ed edede"e#e$efde%e!e!ff ddZ&d ed ede"e#e$efdee%eej'e(feej'e)fffddZ*d ed edefddZ+d ed ede)fddZ,d ede-e)fddZ.d ed ede#fddZ/dede#defdd Z0deddfd!d"Z1d#d$Z2e2d%ej'd&ej'dej'fd'd(Z3e2d%ej'd&ej'dej'fd)d*Z4e2d%ej'd&ej'dej'fd+d,Z5d ede6fd-d.Z7d ed ed/e)defd0d1Z8dS)2N)CallableOptionalUnion)FakeQuantizeBase ObserverBase)_is_activation_post_process)getattr_from_fqn) GraphModule)Node)NSNodeTargetType NSResultsTypec@s4eZdZeZeZeZeZeZ dS)NodeInputOrOutputTypeN) __name__ __module__ __qualname__enumautoFP32INT8FP16UNKNOWNZ FP32_OR_INT8rrC/var/www/auris/lib/python3.10/site-packages/torch/ao/ns/fx/utils.pyrs  rnodegm logger_clsnode_type_to_io_type_mapreturncs|d}|d}|d}|d}|d}|d} |d} |d} |jd krk|j|vr0tjtjfS|j|vr;tjtjfS|j|vrFtjtjfS|j|vret||d } t| tsXJt | |||\} }||fStj tj fS|jd kr|jd kswJt|jt sJt ||jt fd d | D}t|ttfs|rt||d } t| tsJt | |||\} }||fSt fdd |D}t fdd | D}|rtjtjfS|rtjtjfStj tj fS|jdkrc|jdkrt||d }t|tsJt ||||\} }|tjfS|jdkrN  z7get_node_first_input_and_output_type..c3r"r#r$r&r)rrr+`r,c3r"r#r$r&r)rrr+cr, call_method dequantizetor z handling needs to be added)optargetrrrrget_normalized_nth_inputr%r $get_node_first_input_and_output_typerstrranyrrtorchZfloat16)rrrrZFUNS_IO_TYPE_FP32ZFUNS_IO_TYPE_FP16ZFUNS_IO_TYPE_INT8ZFUNS_IO_TYPE_FP32_OR_INT8ZMODS_IO_TYPE_FP32ZMODS_IO_TYPE_INT8MODS_IO_TYPE_FP32_OR_INT8ZMETHS_IO_TYPE_FP32_OR_INT8Z first_argZ_prev_node_input_typeZprev_node_output_type"is_known_fp32_or_int8_input_moduleZis_known_fp32_input_moduleZis_known_int8_input_module prev_nodeZcur_node_dtype_targetrr)rr3&s                               r3cs@t||d}t|ts dS|d}dd}|jdkr=|jtjkr'|||ddS|jtjtj tj tj fvr;|||dd SdS|jd krt|jt sJJt ||jttjtjtjtjtjtjtjtjtjtjtjtjtjtjtjtjtj tj!tj"tj#tj$tjtj%tj&frj'j(fSt)fd d |D}|rt*|||SdS) z{ Returns the qparams (scale, zero_point) of the first input to `node`, if they can be inferred from the graph. rNrcSslt|||}t|||}t|trt|jtsJt|tr$t|jts&Jt||j}t||j}||fSr#)r2r%r r1r4r)rrZ scale_arg_idxZ zp_arg_idxZ scale_nodeZzp_nodeZ scale_objZzp_objrrr _get_scale_zp_from_function_argss    z@get_node_input_qparams.._get_scale_zp_from_function_argsr r r!c3r"r#r$r&Z module_objrrr+r,z)get_node_input_qparams..)+r2r%r r0r1r6Zquantize_per_tensortoqaddZadd_relumulZmul_relur4rnnqZLinearZConv1dZConv2dnniqZ ConvReLU2dZConv3dZ BatchNorm2dZ BatchNorm3dZConvTranspose1dZConvTranspose2dZELUZ GroupNormZInstanceNorm1dZInstanceNorm2dZInstanceNorm3dZ LayerNormZ HardswishZ LeakyReLUZReLU6ZBNReLU2dZBNReLU3dZ ConvReLU1dZ ConvReLU3dZ LinearReLUscaleZ zero_pointr5get_node_input_qparams)rrrr9r7r:r8rr=rrDsb       rDcCs|jdkrQt||j}t|rQt|jdksJt|jdts"J|jd}t|jts/Jt||j}t|rQt|jdksBJt|jdtsLJ|jd}|S)a If node is not an observer, returns it. If node is an observer, navigates up the graph and returns the first parent which is not an observer. For example, graph: (node_non_obs), node = node_non_obs : returns node_non_obs graph: (node_non_obs -> obs0), node = obs0 : returns node_non_obs graph: (node_non_obs -> obs0 -> fq0), node = fq0 : returns node_non_obs r!r r) r0rr1rlenargsr%r r4rrZnode_objrrrreturn_first_non_observer_nodes    rHcCs*|jdkrt||j}t|tjrdSdS)aO Assumes that all non-param args occur first. Returns the number of non-param args expected for a node. For example, for F.linear(x, weight, bias) Returns 1, because x is a non-param arg and weight and bias are params. For lstm_mod(x, hid) Returns 2, because both x and hid are non-param args. r!r;r )r0rr1r%nnZLSTMrGrrrget_number_of_non_param_argss   rJcsptjdkr gSjdkr5jtjtjjjtjfvs(jtj tjjj tj fvr5fddt dD}|SdgS)a- Returns the indices of args of the node which we should attach loggers to, if input logging is enabled. For example, * for (x + y), returns [0, 1] * for (1 + y), returns [1] * for (x + 1), returns [0] * for (linear(x, w, b)) returns [0] * by default, returns [0] rr cs"g|] }tj|tkr|qSr)typerFr )r'irrr ;s"z4get_arg_indices_of_inputs_to_log..r;) rErFr0r1r6r?ops quantizedoperatorr@range)rresultrrMr get_arg_indices_of_inputs_to_log(s  rTcCsRd}|jdvrt|j}|S|jdkr't|jtsJt||j}t|}|S)z Returns a string representation of the type of the function or module pointed to by this node, or '' for other node types. )r r-r!)r0r6typenamer1r%r4r)rrr(Z target_modrrrget_target_type_str@s     rWresults model_namec Cszi}|D]4\}}d}|D]}|D]\}}||kr+t|s$J|dd}qqq|dur6|||<q|||<q|S)a  Rekeys the layer name of a results dictionary to use node names from `model_name`. For example, transforms {'base_op_1_0': {'node_output': {'model_a': [{'ref_node_name': 'linear1', ...}]}}} into {'linear1': {'node_output': {'model_a': [{'ref_node_name': 'linear1', ...}]}}} Note: we cannot use these node names directly because they are not guaranteed to be consistent across models. This is why we extract the results first and rekey afterwards. NrZ ref_node_name)itemsvaluesrE) rXrYZ new_resultsZold_layer_nameresult_type_to_resultsZnew_layer_namemodel_name_to_resultsZcur_model_nameZlist_of_resultsrrr'rekey_logger_info_on_node_name_of_modelOs    r^c Csd}|D]$}|D]}|D]\}}t|dkr(|dddur(|}nq|rb|D]2}|D])}||}|D]\}}||krJqAtt|D]}||d}|||d<qPqAq7q1dSdS)ay If `fqn` entries are filled in for one of the models in `results`, copies them over to any models which do not have them filled out. A common use case benefitting from this is comparing a model prepared by quantization to a quantized model. In this case, the model prepared by quantization would have `fqn` entries, and the quantized model would not. Nrfqn)r[rZrErR) rXZmodel_name_with_fqnsr\r]rYZ model_resultsZref_model_resultsrLr_rrrmaybe_add_missing_fqnsvs4      r`csfddS)Nc s|^}}}t|trt|tst|tr8t|tr8g}t||D]\}}||g|R}||i|q |St|tjrRt|tjrR|jrK|}|jrR|}|j tj ks^|j tj kr`dS||g|R}|i|Sr#) r%tuplelistzipappendr6TensorZ is_quantizedr.Zdtypefloat) rFkwargsZa0Za1Za_otherrXZel0Zel1new_argsfinnerrrrks( zGmaybe_dequantize_first_two_tensor_args_and_handle_tuples..innerr)rjrrir8maybe_dequantize_first_two_tensor_args_and_handle_tuplessrlxycCs*t|}t||}dt||S)z Computes the SQNR between `x` and `y`. Args: x: Tensor or tuple of tensors y: Tensor or tuple of tensors Return: float or tuple of floats )r6Znormlog10)rmrnZPsZPnrrr compute_sqnrs rqcCs"t||d|dS)z Computes the normalized L2 error between `x` and `y`. Args: x: Tensor or tuple of tensors y: Tensor or tuple of tensors Return: float or tuple of floats r;)r6sqrtsumrmrnrrrcompute_normalized_l2_errors" rucCs(|dd}|dd}tjj||S)z Computes the cosine similarity between `x` and `y`. Args: x: Tensor or tuple of tensors y: Tensor or tuple of tensors Return: float or tuple of floats r )Zreshaper6rIZ functionalZcosine_similarityrtrrrcompute_cosine_similaritys  rwcCs4|jdkr|jtjtjtjtjtjtjfvrdSdS)Nr FT)r0r1r6r?r@rQcatstackrMrrrop_type_supports_shadowings  rzidxcCs"z[|j|dd}|dur0|\}}t|t||ksJ|t|kr'||WSt||WSt|jt|j|ks>J|t|jkrK|j|WS|t|j}t|j|WStyt|jt|j|kspJ|t|jkr~|j|YS|t|j}t|j|YSw)zu Given a node, gets the n'th input to that node, normalizing args and kwargs to the best of its ability. T)Znormalize_to_only_use_kwargsN)Znormalized_argumentsrErbr[rFrg RuntimeError)rrr{Znorm_args_and_kwargsZ norm_argsZ norm_kwargsZ kwargs_idxrrrr2s,    r2)9rrQtypingrrrr6Ztorch.ao.nn.intrinsic.quantizedZaorIZ intrinsicrPrBZtorch.ao.nn.quantizedrAZtorch.nnZtorch.ao.quantizationrrZtorch.ao.quantization.observerrZtorch.ao.quantization.utilsrZtorch.fxr Ztorch.fx.graphr Zns_typesr r rOr>Enumrdictr4setrar3rerfintrDrHrJrbrTrWr^r`rlrqrurwboolrzr2rrrrs        {" P   '"