Fi} ddlZddlZddlZddlZddlmZddlmcmZ ddl m Z dZ dZ ddZdZddZdej"d ej"d ej"d ej"d ej"f d Zy)N)uniform_)inverse_sigmoid#multi_scale_deformable_attn_pytorchctjt|Dcgc]}tj|c}Scc}w)aCreate 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 ^/var/www/pod-logistic/pod-ai/venv/lib/python3.12/site-packages/ultralytics/nn/modules/utils.py _get_clonesrs." ==qBA$--/B CCBsAcLttjd|z |z  S)aInitialize conv/fc bias value according to a given probability value. This function calculates the bias initialization value based on a prior probability using the inverse sigmoid (logit) function. It's commonly used in object detection models to initialize classification layers with a specific positive prediction probability. Args: prior_prob (float, optional): Prior probability for bias initialization. Returns: (float): Bias initialization value calculated from the prior probability. Examples: >>> bias = bias_init_with_prob(0.01) >>> print(f"Bias initialization value: {bias:.4f}") Bias initialization value: -4.5951 )floatnplog) prior_probs rbias_init_with_probr#s$& "&&!j.J677 88cdtj|jjdz }t |j| |t |dr&|j t |j | |yyy)aInitialize 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 output dimension. If the module has a bias, it is also initialized. Args: module (nn.Module): Linear module to initialize. Examples: >>> import torch.nn as nn >>> linear = nn.Linear(10, 5) >>> linear_init(linear) rrbiasN)mathsqrtweightshaperhasattrr)r bounds r linear_initr!9se  &----a01 1E V]]UFE*vv6;;#:ufe,$;rc|jdd}|j|}d|z j|}tj||z S)aCalculate the inverse sigmoid function for a tensor. This function applies the inverse of the sigmoid function to a tensor, which is useful in various neural network operations, particularly in attention mechanisms and coordinate transformations. Args: x (torch.Tensor): Input tensor with values in range [0, 1]. eps (float, optional): Small epsilon value to prevent numerical instability. Returns: (torch.Tensor): Tensor after applying the inverse sigmoid function. Examples: >>> x = torch.tensor([0.2, 0.5, 0.8]) >>> inverse_sigmoid(x) tensor([-1.3863, 0.0000, 1.3863]) rr)minmax)r#)clamptorchr)xepsx1x2s rrrMsM$ A1A S B a%3 B 99R"W rvaluevalue_spatial_shapessampling_locationsattention_weightsreturnc:|j\}}}}|j\}}}} } }|j|D cgc] \} } | | z c} } d} d|zdz }g}t|D]\}\} } | |jdj ddj ||z|| | }|dddddd|fj ddjdd}t j||ddd }|j||j ddj ||zd|| | z}tj|d jd |zjd j|||z|}|j ddjScc} } w) aImplement 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, num_heads * 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 rrres2$);; B9j;M;S;S8A{Iz:q4HI&"bb2gIqQJ++a/N$%9:6xB e$,,Q/99!Q?GGYXbdfhjk*!Q5.9CCAqIQQRSUVWMM &Zg]b  ""#456$*33Aq9AA Y; Z(? (b 1 9 9" =@Q Q R b)j(+ 6   Aq ! , , ..;JsF )g{Gz?)gh㈵>)r rnumpyrr&torch.nnrtorch.nn.functional functionalr? torch.nn.initr__all__rrr!rTensorrrrr^s  " BD(9,-(08/ <<8/,,8/ 8/|| 8/  \\ 8/r