a h}. @s~ddlmZmZddlZddlZddlZddlmZmZddlm Z ddl m Z ddl m Z ej jeeeed d d Zd%eeeeedddZGdddZeeedddZeeeedddZejjeeeeeefeeeeeefdddZejjeeefeeeedddZejjeeeeeeeeeeeeed d!d"ZGd#d$d$ejZ dS)&)OptionalUnionN)nnTensorbox_area)_log_api_usage_once) roi_align)levelsunmerged_resultsreturnc Cs|d}|j|j}}tj|d|d|d|df||d}tt|D]h}t||kddddd}| |d||d||d||d}| d|||}qR|S)Nrr rdtypedevice) rrtorchzerossizerangelenwhereviewexpandZscatter)r r Z first_resultrrreslevelindexrE/var/www/auris/lib/python3.9/site-packages/torchvision/ops/poolers.py_onnx_merge_levelss&   r!ư>k_mink_maxcanonical_scalecanonical_levelepscCst|||||SN) LevelMapperr%rrr initLevelMapper%sr-c@s<eZdZdZd eeeeedddZeeedd d Z d S) 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$r%cCs"||_||_||_||_||_dSr+)r&r's0lvl0r*)selfr&r'r(r)r*rrr __init__;s zLevelMapper.__init__)boxlistsrcCsvttdd|D}t|jt||jtj|j|j d}tj ||j |j d}| tj|j  tjS)z< Args: boxlists (list[BoxList]) cSsg|] }t|qSrr).0Zboxlistrrr Oz(LevelMapper.__call__..r)minmax)rsqrtcatfloorr/log2r.tensorr*rclampr&r'toint64)r0r2sZ target_lvlsrrr __call__Is.zLevelMapper.__call__N)r"r#r$) __name__ __module__ __qualname____doc__intfloatr1listrrBrrrr r,/s r,)boxesrcsTtj|dd}|j|jtjfddt|Ddd}tj||gdd}|S)Nr)Zdimc s6g|].\}}tj|ddddf|tjdqS)Nr )rZlayoutr)rZ full_likeZstrided)r3ibrrrr r4[r5z*_convert_to_roi_format..r )rr:rr enumerate)rJZ concat_boxesidsroisrrMr _convert_to_roi_formatWsrQ)feature original_sizercCsb|jdd}g}t||D]<\}}t|t|}dtt|}||q|dS)Nrr)shapeziprHrr=r<roundappend)rRrSrZpossible_scaless1s2Z approx_scalescalerrr _infer_scalebs r\)features image_shapesr(r)rc s|s tdd}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\)r3ZfeatZoriginal_input_shaperr r4zr5z!_setup_scales..r6rr(r)) ValueErrorr8rr<r=float32itemr-rG) r]r^r(r)Zmax_xZmax_yrUscalesZlvl_minZlvl_max map_levelsrr_r _setup_scalesms$  rf)x featmap_namesrcCs,g}|D]\}}||vr ||q |Sr+)itemsrX)rgrh x_filteredkvrrr _filter_inputs  rm)rjrJ output_sizesampling_ratiordmapperrcCs$|dus|durtdt|}t|}|dkrJt|d|||d|dS||}t|} |djd} |dj|dj} } tj| | f|| | d} g}t t ||D]b\}\}}t ||kd}||}t|||||d}t r||| q|| j| |<qt r t||} | S)a Args: x_filtered (List[Tensor]): List of input tensors. boxes (List[Tensor[N, 4]]): boxes to be used to perform the pooling operation, in (x1, y1, x2, y2) format and in the image reference size, not the feature map reference. The coordinate must satisfy ``0 <= x1 < x2`` and ``0 <= y1 < y2``. output_size (Union[List[Tuple[int, int]], List[int]]): size of the output sampling_ratio (int): sampling ratio for ROIAlign scales (Optional[List[float]]): If None, scales will be automatically inferred. Default value is None. mapper (Optional[LevelMapper]): If none, mapper will be automatically inferred. Default value is None. Returns: result (Tensor) Nz$scales and mapper should not be Noner r)rnZ spatial_scaleror)rarrQr rUrrrrrNrVr torchvisionZ _is_tracingrXr?r!)rjrJrnrordrpZ num_levelsrPr Znum_roisZ num_channelsrrresultZtracing_resultsrZper_level_featurer[Z idx_in_levelZrois_per_levelZresult_idx_in_levelrrr _multiscale_roi_alignsT    rscseZdZdZeeeeedZdddee e e e e ee fe e e dfddZ ee efeeee e e fed d d Ze d d dZZS)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]) )rdrer"r#r`)rhrnror(r)csVtt|t|tr$||f}||_||_t||_d|_ d|_ ||_ ||_ dSr+) superr1r isinstancerGrhrotuplernrdrer(r))r0rhrnror(r) __class__rr r1 s   zMultiScaleRoIAlign.__init__)rgrJr^rcCsTt||j}|jdus |jdur:t|||j|j\|_|_t|||j|j |j|jS)a Args: x (OrderedDict[Tensor]): feature maps for each level. They are assumed to have all the same number of channels, but they can have different sizes. boxes (List[Tensor[N, 4]]): boxes to be used to perform the pooling operation, in (x1, y1, x2, y2) format and in the image reference size, not the feature map reference. The coordinate must satisfy ``0 <= x1 < x2`` and ``0 <= y1 < y2``. image_shapes (List[Tuple[height, width]]): the sizes of each image before they have been fed to a CNN to obtain feature maps. This allows us to infer the scale factor for each one of the levels to be pooled. Returns: result (Tensor) N) rmrhrdrerfr(r)rsrnro)r0rgrJr^rjrrr forward!s  zMultiScaleRoIAlign.forward)rcCs&|jjd|jd|jd|jdS)Nz(featmap_names=z, output_size=z, sampling_ratio=))ryrCrhrnro)r0rrr __repr__Cs zMultiScaleRoIAlign.__repr__)rCrDrErFrrIrHr,__annotations__strrrGrwr1dictrrzr| __classcell__rrrxr rts"#  "rt)r"r#r$)!typingrrrZtorch.fxrqrrZtorchvision.ops.boxesrutilsr r ZjitZunusedrIr!rGrHr-r,rQr\Zfxwraprwrfrr~rmrsModulertrrrr sL    (  $ S