o )i.@sddlmZmZmZmZmZddlZddlZddlZddlm Z m Z ddl m Z ddl mZddlmZejjd e d ee d e fd d Z   d2dededededef ddZGdddZdee d e fddZde deed efdd Zejjd!ee d"eeeefdeded eeeeff d#d$Zejjd%eee fd&eed ee fd'd(Zejjd)ee dee d*eed+ed,eeed-eed e fd.d/ZGd0d1d1e jZ dS)3)DictListOptionalTupleUnionN)nnTensorbox_area)_log_api_usage_once) roi_alignlevelsunmerged_resultsreturnc Cs|d}|j|j}}tj|d|d|d|df||d}tt|D]4}t||kddddd}| |d||d||d||d}| d|||}q)|S)Nrr r dtypedevice) rrtorchzerossizerangelenwhereviewexpandZscatter)rrZ first_resultrrreslevelindexr"f/var/www/html/eduruby.in/lip-sync/lip-sync-env/lib/python3.10/site-packages/torchvision/ops/poolers.py_onnx_merge_levelss&   r$ư>k_mink_maxcanonical_scalecanonical_levelepscCst|||||SN) LevelMapper)r(r)r*r+r,r"r"r#initLevelMapper%sr/c @sLeZdZdZ   ddedededed ef d d Zd eed efddZ dS)r.zDetermine which FPN level each RoI in a set of RoIs should map to based on the heuristic in the FPN paper. Args: k_min (int) k_max (int) canonical_scale (int) canonical_level (int) eps (float) r%r&r'r(r)r*r+r,cCs"||_||_||_||_||_dSr-)r(r)s0lvl0r,)selfr(r)r*r+r,r"r"r#__init__;s  zLevelMapper.__init__boxlistsrcCsvttdd|D}t|jt||jtj|j|j d}tj ||j |j d}| tj|j  tjS)z< Args: boxlists (list[BoxList]) cSsg|]}t|qSr"r ).0Zboxlistr"r"r# Osz(LevelMapper.__call__..r)minmax)rsqrtcatfloorr1log2r0tensorr,rclampr(r)toZint64)r2r4sZ target_lvlsr"r"r#__call__Is.zLevelMapper.__call__Nr%r&r') __name__ __module__ __qualname____doc__intfloatr3rrrBr"r"r"r#r./s" r.boxescsTtj|dd}|j|jtjfddt|Ddd}tj||gdd}|S)Nr)dimc s6g|]\}}tj|ddddf|tjdqS)Nr )rZlayoutr)rZ full_likeZstrided)r5ibrrr"r#r6[s6z*_convert_to_roi_format..r )rr;rr enumerate)rJZ concat_boxesZidsroisr"rNr#_convert_to_roi_formatWsrQfeature original_sizecCsb|jdd}g}t||D]\}}t|t|}dtt|}||q|dS)Nr r)shapeziprIrr>r=roundappend)rRrSrZpossible_scaless1s2Z approx_scalescaler"r"r# _infer_scalebs r\features image_shapesc s|stdd}d}|D]}t|d|}t|d|}q ||ffdd|D}ttj|dtjd }ttj|dtjd } tt|t| ||d} || fS) Nzimages list should not be emptyrr csg|]}t|qSr")r\)r5ZfeatZoriginal_input_shaper"r#r6zsz!_setup_scales..r7rr*r+) ValueErrorr9rr=r>Zfloat32itemr/rH) r]r^r*r+Zmax_xZmax_yrUscalesZlvl_minZlvl_max map_levelsr"r_r# _setup_scalesms$  rex featmap_namescCs,g}|D] \}}||vr||q|Sr-)itemsrX)rfrg x_filteredkvr"r"r# _filter_inputs  rlri output_sizesampling_ratiorcmappercCs"|dus|dur tdt|}t|}|dkr%t|d|||d|dS||}t|} |djd} |dj|dj} } tj| | f|| | d} g}t t ||D]1\}\}}t ||kd}||}t|||||d}t r}||| qT|| j| |<qTt rt||} | S)a Args: x_filtered (List[Tensor]): List of input tensors. boxes (List[Tensor[N, 4]]): boxes to be used to perform the pooling operation, in (x1, y1, x2, y2) format and in the image reference size, not the feature map reference. The coordinate must satisfy ``0 <= x1 < x2`` and ``0 <= y1 < y2``. output_size (Union[List[Tuple[int, int]], List[int]]): size of the output sampling_ratio (int): sampling ratio for ROIAlign scales (Optional[List[float]]): If None, scales will be automatically inferred. Default value is None. mapper (Optional[LevelMapper]): If none, mapper will be automatically inferred. Default value is None. Returns: result (Tensor) Nz$scales and mapper should not be Noner r)rmZ spatial_scalernr)rarrQrrUrrrrrOrVr torchvisionZ _is_tracingrXr@r$)rirJrmrnrcroZ num_levelsrPrZnum_roisZ num_channelsrrresultZtracing_resultsr Zper_level_featurer[Z idx_in_levelZrois_per_levelZresult_idx_in_levelr"r"r#_multiscale_roi_alignsT   rrc seZdZdZeeeeedZddddee de e e e ee fde d e d e f fd d Z d ee efdeedee e e fdefddZde fddZZS)MultiScaleRoIAligna{ Multi-scale RoIAlign pooling, which is useful for detection with or without FPN. It infers the scale of the pooling via the heuristics specified in eq. 1 of the `Feature Pyramid Network paper `_. They keyword-only parameters ``canonical_scale`` and ``canonical_level`` correspond respectively to ``224`` and ``k0=4`` in eq. 1, and have the following meaning: ``canonical_level`` is the target level of the pyramid from which to pool a region of interest with ``w x h = canonical_scale x canonical_scale``. Args: featmap_names (List[str]): the names of the feature maps that will be used for the pooling. output_size (List[Tuple[int, int]] or List[int]): output size for the pooled region sampling_ratio (int): sampling ratio for ROIAlign canonical_scale (int, optional): canonical_scale for LevelMapper canonical_level (int, optional): canonical_level for LevelMapper Examples:: >>> m = torchvision.ops.MultiScaleRoIAlign(['feat1', 'feat3'], 3, 2) >>> i = OrderedDict() >>> i['feat1'] = torch.rand(1, 5, 64, 64) >>> i['feat2'] = torch.rand(1, 5, 32, 32) # this feature won't be used in the pooling >>> i['feat3'] = torch.rand(1, 5, 16, 16) >>> # create some random bounding boxes >>> boxes = torch.rand(6, 4) * 256; boxes[:, 2:] += boxes[:, :2] >>> # original image size, before computing the feature maps >>> image_sizes = [(512, 512)] >>> output = m(i, [boxes], image_sizes) >>> print(output.shape) >>> torch.Size([6, 5, 3, 3]) )rcrdr%r&r`rgrmrnr*r+csVtt|t|tr||f}||_||_t||_d|_ d|_ ||_ ||_ dSr-) superr3r isinstancerHrgrntuplermrcrdr*r+)r2rgrmrnr*r+ __class__r"r#r3 s    zMultiScaleRoIAlign.__init__rfrJr^rcCsTt||j}|jdus|jdurt|||j|j\|_|_t|||j|j |j|jS)a Args: x (OrderedDict[Tensor]): feature maps for each level. They are assumed to have all the same number of channels, but they can have different sizes. boxes (List[Tensor[N, 4]]): boxes to be used to perform the pooling operation, in (x1, y1, x2, y2) format and in the image reference size, not the feature map reference. The coordinate must satisfy ``0 <= x1 < x2`` and ``0 <= y1 < y2``. image_shapes (List[Tuple[height, width]]): the sizes of each image before they have been fed to a CNN to obtain feature maps. This allows us to infer the scale factor for each one of the levels to be pooled. Returns: result (Tensor) N) rlrgrcrdrer*r+rrrmrn)r2rfrJr^rir"r"r#forward!s   zMultiScaleRoIAlign.forwardcCs&|jjd|jd|jd|jdS)Nz(featmap_names=z, output_size=z, sampling_ratio=))rxrDrgrmrn)r2r"r"r#__repr__Cs zMultiScaleRoIAlign.__repr__)rDrErFrGrrrIr.__annotations__strrrHrr3rrryr{ __classcell__r"r"rwr#rss4#  "rsrC)!typingrrrrrrZtorch.fxrprrZtorchvision.ops.boxesr utilsr rZjitZunusedr$rHrIr/r.rQr\Zfxwraprer}rlrrModulersr"r"r"r#st     (   (  S