MCPcopy Create free account

hub / github.com/OliverRensu/ARM / functions

Functions161 in github.com/OliverRensu/ARM

⨍ Functions 161◇ Types & classes 24
Function_load_checkpoint_for_ema
Workaround for ModelEma._load_checkpoint to accept an already-loaded object
Finetuning/util/misc.py:317
Functionadjust_learning_rate
Decay the learning rate with half-cycle cosine after warmup
utils/lr_sched.py:3
Functionadjust_learning_rate
Decay the learning rate with half-cycle cosine after warmup
Finetuning/util/lr_sched.py:9
Functionall_reduce_mean
(x)
utils/misc.py:360
Functionall_reduce_mean
(x)
Finetuning/util/misc.py:350
Methodallocate_inference_cache
(self, batch_size, max_seqlen, dtype=None, **kwargs)
models_pretrain.py:409
Methodallocate_inference_cache
(self, batch_size, max_seqlen, dtype=None, **kwargs)
mamba_simple.py:596
Methodallocate_inference_cache
(self, batch_size, max_seqlen, dtype=None, **kwargs)
Finetuning/mamba_simple.py:599
Methodallocate_inference_cache
(self, batch_size, max_seqlen, dtype=None, **kwargs)
Finetuning/models_mamba.py:114
Functionarm_base_pz16
(pretrained=False, **kwargs)
models_pretrain.py:513
Functionarm_base_pz16
(pretrained=False, **kwargs)
Finetuning/models_mamba.py:402
Functionarm_huge_pz16
(pretrained=False, **kwargs)
models_pretrain.py:529
Functionarm_huge_pz16
(pretrained=False, **kwargs)
Finetuning/models_mamba.py:429
Functionarm_large_pz16
(pretrained=False, **kwargs)
models_pretrain.py:521
Functionarm_large_pz16
(pretrained=False, **kwargs)
Finetuning/models_mamba.py:416
Methodatten_init_weights
(self, m)
models_pretrain.py:399
Methodavg
(self)
utils/misc.py:56
Methodavg
(self)
Finetuning/util/misc.py:61
Functionbuild_dataset
(is_train, args)
utils/datasets.py:16
Functionfinetune_load_model
(args, model_without_ddp, optimizer, loss_scaler, model_ema)
utils/misc.py:338
Functionfinetune_save_model
(args, epoch, model, model_without_ddp, optimizer, loss_scaler, model_ema, max_accuracy, ema_max_accuracy)
utils/misc.py:300
Methodforward
(self, x)
models_pretrain.py:45
Methodforward
(self, q, kv, mask)
models_pretrain.py:69
Methodforward
(self, q, kv, mask)
models_pretrain.py:101
Methodforward
(self, x)
models_pretrain.py:126
Methodforward
(self, x)
models_pretrain.py:154
Methodforward
( self, hidden_states: Tensor, residual: Optional[Tensor] = None, inference_params=None )
models_pretrain.py:189
Methodforward
(self, x, inference_params=None)
models_pretrain.py:505
Methodforward
hidden_states: (B, L, D) Returns: same shape as hidden_states
mamba_simple.py:250
Methodforward
r"""Pass the input through the encoder layer. Args: hidden_states: the sequence to the encoder layer (required). resi
mamba_simple.py:568
Methodforward
hidden_states: (B, L, D) Returns: same shape as hidden_states
Finetuning/mamba_simple.py:253
Methodforward
r"""Pass the input through the encoder layer. Args: hidden_states: the sequence to the encoder layer (required). resi
Finetuning/mamba_simple.py:571
Methodforward
(self, x)
Finetuning/models_mamba.py:44
Methodforward
(self, x)
Finetuning/models_mamba.py:72
Methodforward
( self, hidden_states: Tensor, residual: Optional[Tensor] = None, inference_params=None )
Finetuning/models_mamba.py:106
Methodforward
(self, x, return_features=False, inference_params=None, if_random_cls_token_position=False, if_random_token_ra
Finetuning/models_mamba.py:392
Functionget_2d_sincos_pos_embed
grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/
Finetuning/util/pos_embed.py:20
Methodget_params
(img, scale, ratio)
utils/crop.py:24
Methodget_params
(img, scale, ratio)
Finetuning/util/crop.py:23
Methodglobal_avg
(self)
utils/misc.py:61
Methodglobal_avg
(self)
Finetuning/util/misc.py:66
Functioninit_distributed_mode
(args)
utils/misc.py:211
Functioninit_distributed_mode
(args)
Finetuning/util/misc.py:216
Functioninterpolate_pos_embed
(model, checkpoint_model)
utils/pos_embed.py:73
Functionload_model
(args, model_without_ddp, optimizer, loss_scaler)
utils/misc.py:322
Functionload_model
(args, model_without_ddp, optimizer, loss_scaler, model_ema)
Finetuning/util/misc.py:326
Methodload_pretrained
(self, checkpoint_path, prefix="")
models_pretrain.py:420
Methodload_pretrained
(self, checkpoint_path, prefix="")
Finetuning/models_mamba.py:353
Methodmedian
(self)
utils/misc.py:51
Methodmedian
(self)
Finetuning/util/misc.py:56
Methodno_weight_decay
(self)
models_pretrain.py:416
Functionparam_groups_lrd
Parameter groups for layer-wise lr decay Following BEiT: https://github.com/microsoft/unilm/blob/master/beit/optim_factory.py#L58
utils/lr_decay.py:17
Functionparam_groups_lrd
Parameter groups for layer-wise lr decay Following BEiT: https://github.com/microsoft/unilm/blob/master/beit/optim_factory.py#L58
Finetuning/util/lr_decay.py:15
Functionsave_model
(args, epoch, model, model_without_ddp, optimizer, loss_scaler)
utils/misc.py:280
Functionsave_model
(args, epoch, model, model_without_ddp, optimizer, loss_scaler, model_ema, max_accuracy, ema_max_accuracy)
Finetuning/util/misc.py:295
Functionsegm_init_weights
(m)
models_pretrain.py:270
Functionsegm_init_weights
(m)
Finetuning/models_mamba.py:188
Methodsynchronize_between_processes
Warning: does not synchronize the deque!
utils/misc.py:37
Methodsynchronize_between_processes
Warning: does not synchronize the deque!
Finetuning/util/misc.py:42
Methodvalue
(self)
utils/misc.py:69
Methodvalue
(self)
Finetuning/util/misc.py:74
← previous101–161 of 161, ranked by callers