h SSKrSSKrSSKrSSKrSSKJr SSKJs Jr SSK J r Sr Sr SSjrSrSSjrS\R"S \R"S \R"S \R"S \R"4 S jrg)N)uniform_)#multi_scale_deformable_attn_pytorchinverse_sigmoidc[R"[U5Vs/sHn[R"U5PM sn5$s snf)az Create a list of cloned modules from the given module. Args: module (nn.Module): The module to be cloned. n (int): Number of clones to create. Returns: (nn.ModuleList): A ModuleList containing n clones of the input module. Examples: >>> import torch.nn as nn >>> layer = nn.Linear(10, 10) >>> clones = _get_clones(layer, 3) >>> len(clones) 3 )nn ModuleListrangecopydeepcopy)modulen_s V/home/james-whalen/.local/lib/python3.13/site-packages/ultralytics/nn/modules/utils.py _get_clonesrs2$ ==qBA$--/B CCBs AcN[[R"SU- U- 5*5$)a Initialize conv/fc bias value according to a given probability value. This function calculates the bias initialization value based on a prior probability using the inverse error function. It's commonly used in object detection models to initialize classification layers with a specific positive prediction probability. Args: prior_prob (float, optional): Prior probability for bias initialization. Returns: (float): Bias initialization value calculated from the prior probability. Examples: >>> bias = bias_init_with_prob(0.01) >>> print(f"Bias initialization value: {bias:.4f}") Bias initialization value: -4.5951 )floatnplog) prior_probs rbias_init_with_probr$s$& "&&!j.J677 88cS[R"URRS5- n[ URU*U5 [ US5(a'UR b[ UR U*U5 ggg)a Initialize the weights and biases of a linear module. This function initializes the weights of a linear module using a uniform distribution within bounds calculated from the input dimension. If the module has a bias, it is also initialized. Args: module (nn.Module): Linear module to initialize. Returns: (nn.Module): The initialized module. Examples: >>> import torch.nn as nn >>> linear = nn.Linear(10, 5) >>> initialized_linear = linear_init(linear) rrbiasN)mathsqrtweightshaperhasattrr)r bounds r linear_initr!:sh$  &----a01 1E V]]UFE*vv6;;#:ufe,$;rcURSSS9nURUS9nSU- RUS9n[R"X#- 5$)a[ Calculate the inverse sigmoid function for a tensor. This function applies the inverse of the sigmoid function to a tensor, which is useful in various neural network operations, particularly in attention mechanisms and coordinate transformations. Args: x (torch.Tensor): Input tensor with values in range [0, 1]. eps (float, optional): Small epsilon value to prevent numerical instability. Returns: (torch.Tensor): Tensor after applying the inverse sigmoid function. Examples: >>> x = torch.tensor([0.2, 0.5, 0.8]) >>> inverse_sigmoid(x) tensor([-1.3863, 0.0000, 1.3863]) rr)minmax)r#)clamptorchr)xepsx1x2s rrrRsK& A1A S B a%3 B 99RW rvaluevalue_spatial_shapessampling_locationsattention_weightsreturnc URupEpgURupXpipURUV V s/sH upX-PM sn n SS9n SU-S- n/n[U5HunupU URS5R SS5R XF-X{U 5nUSS2SS2SS2U4R SS5RSS5n[ R"UUSSSS 9nURU5 M UR SS5R XF-SXU -5n[R"US S9RS 5U-RS 5RXFU-U5nUR SS5R5$s sn n f) a| Implement multi-scale deformable attention in PyTorch. This function performs deformable attention across multiple feature map scales, allowing the model to attend to different spatial locations with learned offsets. Args: value (torch.Tensor): The value tensor with shape (bs, num_keys, num_heads, embed_dims). value_spatial_shapes (torch.Tensor): Spatial shapes of the value tensor with shape (num_levels, 2). sampling_locations (torch.Tensor): The sampling locations with shape (bs, num_queries, num_heads, num_levels, num_points, 2). attention_weights (torch.Tensor): The attention weights with shape (bs, num_queries, num_heads, num_levels, num_points). Returns: (torch.Tensor): The output tensor with shape (bs, num_queries, embed_dims). References: https://github.com/IDEA-Research/detrex/blob/main/detrex/layers/multi_scale_deform_attn.py r)dimNrbilinearzerosF)mode padding_mode align_corners)rsplit enumerateflatten transposereshapeF grid_sampleappendr&stacksumview contiguous)r+r,r-r.bsr num_heads embed_dims num_queries num_levels num_pointsH_W_ value_listsampling_gridssampling_value_listlevelvalue_l_sampling_grid_l_sampling_value_l_outputs rrrks4$);; B9;M;S;S8AI:4HI4H&"bg4HIqQJ++a/N$%9:x e$,,Q/99!Q?GGXbhjk*!Q5.9CCAqIQQRSUVWMM &Zg]b  ""#45;$*33Aq9AA ;Z(? (b 1 9 9" =@Q Q R bj(+ 6   Aq ! , , ..;JsF )g{Gz?)gh㈵>)r rnumpyrr&torch.nnrtorch.nn.functional functionalr? torch.nn.initr__all__rrr!rTensorrrrr^s  " BD*9,-029/ <<9/,,9/ 9/|| 9/  \\ 9/r