a  d,@s8ddlZddlZddlZddlZddlZddlmZddlm Z ddlm Z ddl m Z ddl mZddlmZddlmZmZdd lmZed,d d Zd dZGddde jZGddde jZd-ddZd.ddZddZGdddeZ dd Z!d/d%d&Z"d'd(Z#e#d Z$e#d)Z%e#d*Z&e#d+Z'e#Z(dS)0N) LooseVersion)repeat)nn) functional)init) _BatchNorm)ModulatedDeformConvPackmodulated_deform_conv)get_root_loggercKst|ts|g}|D]}|D]}t|tjrntj|jfi||jj|9_|j dur|j j |q t|tj rtj|jfi||jj|9_|j dur|j j |q t|t r t |jd|j dur |j j |q qdS)aeInitialize network weights. Args: module_list (list[nn.Module] | nn.Module): Modules to be initialized. scale (float): Scale initialized weights, especially for residual blocks. Default: 1. bias_fill (float): The value to fill bias. Default: 0 kwargs (dict): Other arguments for initialization function. Nr ) isinstancelistmodulesrConv2drZkaiming_normal_weightdatabiasZfill_ZLinearrZ constant_)Z module_listscaleZ bias_fillkwargsmodulemr`/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/basicsr/archs/arch_util.pydefault_init_weightss$        rcKs0g}t|D]}||fi|q tj|S)zMake layers by stacking the same blocks. Args: basic_block (nn.module): nn.module class for basic block. num_basic_block (int): number of blocks. Returns: nn.Sequential: Stacked blocks in nn.Sequential. )rangeappendr Sequential)Z basic_blockZnum_basic_blockkwargZlayers_rrr make_layer0s  rcs*eZdZdZd fdd ZddZZS) ResidualBlockNoBNaResidual block without BN. It has a style of: ---Conv-ReLU-Conv-+- |________________| Args: num_feat (int): Channel number of intermediate features. Default: 64. res_scale (float): Residual scale. Default: 1. pytorch_init (bool): If set to True, use pytorch default init, otherwise, use default_init_weights. Default: False. @r Fcsltt|||_tj||ddddd|_tj||ddddd|_tjdd|_ |sht |j|jgddS)Nr T)r)Zinplaceg?) superr __init__ res_scalerrconv1conv2ZReLUrelur)selfnum_featr%Z pytorch_init __class__rrr$OszResidualBlockNoBN.__init__cCs(|}||||}|||jSN)r'r(r&r%)r)xidentityoutrrrforwardYszResidualBlockNoBN.forward)r!r F)__name__ __module__ __qualname____doc__r$r1 __classcell__rrr+rr @s r cs eZdZdZfddZZS)UpsamplezUpsample module. Args: scale (int): Scale factor. Supported scales: 2^n and 3. num_feat (int): Channel number of intermediate features. c sg}||d@dkr\ttt|dD]0}|t|d|ddd|tdq(nF|dkr|t|d|ddd|tdntd|dt t |j |dS) Nr rr" zscale z/ is not supported. Supported scales: 2^n and 3.) rintmathlogrrrZ PixelShuffle ValueErrorr#r7r$)r)rr*rrr+rrr$gszUpsample.__init__)r2r3r4r5r$r6rrr+rr7_sr7bilinearzerosTcCs|dd|ddks$J|\}}}}ttd||td||\}} t| |fd} d| _| |} d| dddddddft|ddd } d| dddddddft|ddd } tj| | fdd }t j |||||d }|S) akWarp an image or feature map with optical flow. Args: x (Tensor): Tensor with size (n, c, h, w). flow (Tensor): Tensor with size (n, h, w, 2), normal value. interp_mode (str): 'nearest' or 'bilinear'. Default: 'bilinear'. padding_mode (str): 'zeros' or 'border' or 'reflection'. Default: 'zeros'. align_corners (bool): Before pytorch 1.3, the default value is align_corners=True. After pytorch 1.3, the default value is align_corners=False. Here, we use the True as default. Returns: Tensor: Warped image or feature map. Nr r"rr8F@?Zdim)mode padding_mode align_corners) sizetorchZmeshgridZarangeZtype_asstackfloatZ requires_gradmaxFZ grid_sample)r.flow interp_moderFrGrhwZgrid_yZgrid_xZgridZvgridZvgrid_xZvgrid_yZ vgrid_scaledoutputrrr flow_warpus$,22rSFcCs|\}}}}|dkr 1.0). 2) The order of output_size should be [out_h, out_w]. interp_mode (str): The mode of interpolation for resizing. Default: 'bilinear'. align_corners (bool): Whether align corners. Default: False. Returns: Tensor: Resized flow. Zratiorr shapez1Size type should be ratio or shape, but got type .N)inputrHrErG)rHr;r>clonerMZ interpolate)rNZ size_typesizesrOrGrZflow_hZflow_wZoutput_hZoutput_wZ input_flowZratio_hZratio_wZ resized_flowrrr resize_flows$$$ rYc Cs||\}}}}||d}||dkr4||dks8J||}||}|||||||} | dddddd||||S)z Pixel unshuffle. Args: x (Tensor): Input feature with shape (b, c, hh, hw). scale (int): Downsample ratio. Returns: Tensor: the pixel unshuffled feature. r8rr r"r9)rHviewZpermuteZreshape) r.rbchhZhwZ out_channelrPrQZx_viewrrrpixel_unshuffles  r_c@seZdZdZddZdS) DCNv2PackaNModulated deformable conv for deformable alignment. Different from the official DCNv2Pack, which generates offsets and masks from the preceding features, this DCNv2Pack takes another different features to generate offsets and masks. Ref: Delving Deep into Deformable Alignment in Video Super-Resolution. c Cs||}tj|ddd\}}}tj||fdd}t|}tt|}|dkrlt} | d|dt t j t dkrt j |||j|j|j|j|j|St||||j|j|j|j|j|j|j SdS)Nr"r rD2zOffset abs mean is z, larger than 50.z0.9.0)Z conv_offsetrIchunkcatZsigmoidmeanabsr warningr torchvision __version__opsZ deform_conv2drrZstridepaddingZdilationr groupsZdeformable_groups) r)r.Zfeatr0Zo1Zo2maskoffsetZoffset_absmeanloggerrrrr1s   zDCNv2Pack.forwardN)r2r3r4r5r1rrrrr`s r`cCsdd}||d|ks(||d|kr6tjdddt||||}||||}|d|dd|d|||td| ||j ||d|WdS1s0YdS) NcSsdt|tddS)NrCrB)r<erfsqrtr.rrrnorm_cdfsz(_no_grad_trunc_normal_..norm_cdfr8zjmean is more than 2 std from [a, b] in nn.init.trunc_normal_. The distribution of values may be incorrect.) stacklevelr rB)minrL) warningswarnrIno_gradZuniform_Zerfinv_Zmul_r<rpZadd_Zclamp_)tensorrdstdar\rrlowZuprrr_no_grad_trunc_normal_s   r|rCrBcCst|||||S)a?Fills the input Tensor with values drawn from a truncated normal distribution. From: https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/layers/weight_init.py The values are effectively drawn from the normal distribution :math:`\mathcal{N}(\text{mean}, \text{std}^2)` with values outside :math:`[a, b]` redrawn until they are within the bounds. The method used for generating the random values works best when :math:`a \leq \text{mean} \leq b`. Args: tensor: an n-dimensional `torch.Tensor` mean: the mean of the normal distribution std: the standard deviation of the normal distribution a: the minimum cutoff value b: the maximum cutoff value Examples: >>> w = torch.empty(3, 5) >>> nn.init.trunc_normal_(w) )r|)rxrdryrzr\rrr trunc_normal_srcsfdd}|S)Ncs t|tjjr|Stt|Sr-)r collectionsabcIterabletuplerrqnrrparse2sz_ntuple..parser)rrrrr_ntuple0s rr8r"r9)r r)r?r@T)r?F)r}rCr~rB))collections.abcrr<rIrgruZdistutils.versionr itertoolsrrZtorch.nnrrMrZtorch.nn.modules.batchnormrZbasicsr.ops.dcnrr Z basicsr.utilsr rwrrModuler rr7rSrYr_r`r|rrZ to_1tupleZ to_2tupleZ to_3tupleZ to_4tupleZ to_ntuplerrrrs:         " '&