+  °³js ãó<€^RIt^RIHuHt^RIHtRRRlltR#)éN)Ú_log_api_usage_oncec óœ€V^8„dQhR\PR\PR\R\R\R\P/#)éÚinputsÚtargetsÚalphaÚgammaÚ reductionÚreturn)ÚtorchÚTensorÚfloatÚstr)Úformats"Ú[/home/luca/screen-checking/.venv/lib/python3.14/site-packages/torchvision/ops/focal_loss.pyÚ __annotate__rsP€÷6ñ6Ü L‰Lð6ä \‰\ð6ô ð6ô ð 6ô ð 6ô  ‡\\ñ 6ócóÌ€^Tu;8:d^8:gMVR 8wd\RV R24h\PP4'g4\PP 4'g\ \ 4\P!V4p\P!WRR7pWQ,^V, ^V, ,,pV^V, V,,pV^8¼d-W!,^V, ^V, ,,p W˜,pVR8XdV#VR8XdVP4pV#VR8XdVP4pV#\RV R24h) aÖ Loss used in RetinaNet for dense detection: https://arxiv.org/abs/1708.02002. Args: inputs (Tensor): A float tensor of arbitrary shape. The predictions for each example. targets (Tensor): A float tensor with the same shape as inputs. Stores the binary classification label for each element in inputs (0 for the negative class and 1 for the positive class). alpha (float): Weighting factor in range [0, 1] to balance positive vs negative examples or -1 for ignore. Default: ``0.25``. gamma (float): Exponent of the modulating factor (1 - p_t) to balance easy vs hard examples. Default: ``2``. reduction (string): ``'none'`` | ``'mean'`` | ``'sum'`` ``'none'``: No reduction will be applied to the output. ``'mean'``: The output will be averaged. ``'sum'``: The output will be summed. Default: ``'none'``. Returns: Loss tensor with the reduction option applied. zInvalid alpha value: z4. alpha must be in the range [0,1] or -1 for ignore.Únone)r ÚmeanÚsumz$Invalid Value for arg 'reduction': 'z3 Supported reduction modes: 'none', 'mean', 'sum'éÿÿÿÿ) Ú ValueErrorr ÚjitÚ is_scriptingÚ is_tracingrÚsigmoid_focal_lossÚsigmoidÚFÚ binary_cross_entropy_with_logitsrr) rrrr r ÚpÚce_lossÚp_tÚlossÚalpha_ts &&&&& rrrs4€ð: ŽO˜!ŽO ¨"¤ÜÐ0°°Ð7kÐlÓmÐmä 9‰9× !Ñ !× #Ò #¬E¯I©I×,@Ñ,@×,BÒ,BÜÔ.Ô/Ü Š fÓ€AÜ×0Ò0°ÈFÔS€GØ +˜˜Q 1 w¥;Õ/Õ /€CØ q˜3•w 5Õ(Õ )€Dà „zØ•/ Q¨¥Y°1°wµ;Õ$?Õ?ˆØ~ˆðFÔØ ð €Kð fÔ Øy‰y‹{ˆð €Kð eÔ Øx‰x‹zˆð €KôØ2°9°+Ð=qÐ ró ð r)gÐ?rr)r Útorch.nn.functionalÚnnÚ functionalrÚutilsrr©rrÚr+sðÛ ßÐå'÷6ñ6r