MCPcopy Create free account

hub / github.com/amazon-science/mm-cot / functions

Functions1,823 in github.com/amazon-science/mm-cot

⨍ Functions 1,823◇ Types & classes 268
↓ 2 callersFunction_create_visformer
(variant, pretrained=False, default_cfg=None, **kwargs)
timm/models/visformer.py:315
↓ 2 callersFunction_decode_and_center_crop
Crops to center of image with padding then scales image_size.
timm/data/tf_preprocessing.py:113
↓ 2 callersFunction_download_from_hf
(model_id: str, filename: str)
timm/models/hub.py:77
↓ 2 callersMethod_erase
(self, img, chan, img_h, img_w, dtype)
timm/data/random_erasing.py:68
↓ 2 callersMethod_filename
(self, index, basename=False, absolute=False)
timm/data/parsers/parser.py:9
↓ 2 callersFunction_gen_mixnet_s
Creates a MixNet Small model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet Paper: https://arxiv.org
timm/models/efficientnet.py:1035
↓ 2 callersFunction_get_feature_info
(net, out_indices)
timm/models/features.py:135
↓ 2 callersMethod_get_lr
(self, t)
timm/scheduler/cosine_lr.py:68
↓ 2 callersMethod_get_lr
(self, t)
timm/scheduler/step_lr.py:46
↓ 2 callersFunction_init_vit_weights
ViT weight initialization * When called without n, head_bias, jax_impl args it will behave exactly the same as my original init for compati
timm/models/vision_transformer.py:363
↓ 2 callersMethod_lazy_init
Lazily initialize the dataset. This is necessary to init the Tensorflow dataset pipeline in the (dataloader) process that will be us
timm/data/parsers/parser_tfds.py:86
↓ 2 callersMethod_make_conv_level
(self, inplanes, planes, convs, stride=1, dilation=1)
timm/models/dla.py:301
↓ 2 callersMethod_make_head
(self, pre_stage_channels, incre_only=False)
timm/models/hrnet.py:575
↓ 2 callersMethod_make_layer
(self, block, inplanes, planes, blocks, stride=1)
timm/models/hrnet.py:640
↓ 2 callersFunction_module_list
(module, flatten_sequential=False)
timm/models/features.py:121
↓ 2 callersMethod_normalize
(self, x)
timm/data/dataset.py:134
↓ 2 callersMethod_params_per_batch
(self)
timm/data/mixup.py:141
↓ 2 callersMethod_rms
(tensor)
timm/optim/adafactor.py:73
↓ 2 callersMethod_save
(self, save_path, epoch, metric=None)
timm/utils/checkpoint_saver.py:99
↓ 2 callersFunction_scale_stage_depth
Per-stage depth scaling Scales the block repeats in each stage. This depth scaling impl maintains compatibility with the EfficientNet scaling
timm/models/efficientnet_builder.py:200
↓ 2 callersMethod_set_transforms
(self, x)
timm/data/dataset.py:120
↓ 2 callersMethod_update
(self, model, update_fn)
timm/utils/model_ema.py:115
↓ 2 callersMethodbottleneck_fn
(self, xs)
timm/models/densenet.py:60
↓ 2 callersFunctionbuild_train_pair
(problems, test_qid, args, curr_le_data=None)
utils_prompt.py:195
↓ 2 callersFunctioncaculate_bleu
(results, data, gram)
evaluations.py:35
↓ 2 callersMethodcell_forward
(self, x_left, x_right)
timm/models/pnasnet.py:120
↓ 2 callersFunctioncreate_parser
(name, root, split='train', **kwargs)
timm/data/parsers/parser_factory.py:8
↓ 2 callersFunctioncreate_resnetv2_stem
( in_chs, out_chs=64, stem_type='', preact=True, conv_layer=StdConv2d, norm_layer=partial(Grou
timm/models/resnetv2.py:298
↓ 2 callersFunctioncreate_transform
( input_size, is_training=False, use_prefetcher=False, no_aug=False, s
timm/data/transforms_factory.py:167
↓ 2 callersFunctiondispatch_clip_grad
Dispatch to gradient clipping method Args: parameters (Iterable): model parameters to clip value (float): clipping value/factor/
timm/utils/clip_grad.py:6
↓ 2 callersMethodforward_features
(self, x)
timm/models/dla.py:321
↓ 2 callersMethodforward_features
(self, x0)
timm/models/coat.py:488
↓ 2 callersMethodforward_postaux
(self, x)
timm/models/inception_v3.py:373
↓ 2 callersMethodforward_preaux
(self, x)
timm/models/inception_v3.py:339
↓ 2 callersMethodget_attention
(self, x)
timm/models/convit.py:90
↓ 2 callersMethodget_attention_biases
(self, device: torch.device)
timm/models/levit.py:270
↓ 2 callersMethodget_attention_biases
(self, device: torch.device)
timm/models/levit.py:364
↓ 2 callersFunctionget_cache_dir
Returns the location of the directory where models are cached (and creates it if necessary).
timm/models/hub.py:26
↓ 2 callersMethodget_cycle_length
(self, cycles=0)
timm/scheduler/tanh_lr.py:113
↓ 2 callersFunctionget_padding
(kernel_size, stride, dilation=1)
timm/models/resnet.py:277
↓ 2 callersFunctionget_state_dict
(model, unwrap_fn=unwrap_model)
timm/utils/model.py:16
↓ 2 callersMethodinit_weights
(self, nlhb=False)
timm/models/mlp_mixer.py:275
↓ 2 callersFunctionis_stem_deep
(stem_type)
timm/models/resnetv2.py:294
↓ 2 callersMethodload_pretrained
(self, checkpoint_path, prefix='resnet/')
timm/models/resnetv2.py:391
↓ 2 callersFunctionmixup_target
(target, num_classes, lam=1., smoothing=0.0, device='cuda')
timm/data/mixup.py:22
↓ 2 callersFunctionone_hot
(x, num_classes, on_value=1., off_value=0., device='cuda')
timm/data/mixup.py:17
↓ 2 callersFunctionoverlay_external_default_cfg
Overlay 'external_default_cfg' in kwargs on top of default_cfg arg.
timm/models/helpers.py:337
↓ 2 callersFunctionreduce_feat_size
(feat_size, stride=2)
timm/models/byobnet.py:949
↓ 2 callersFunctionresnet26d
Constructs a ResNet-26-D model.
timm/models/resnet.py:742
↓ 2 callersFunctionresnet50d
Constructs a ResNet-50-D model.
timm/models/resnet.py:758
↓ 2 callersFunctionsplit_model_name
(model_name)
timm/models/factory.py:7
↓ 2 callersMethodstep
(self, closure=None)
timm/optim/sgdp.py:55
↓ 2 callersFunctiontokenize
(text)
evaluations.py:13
↓ 2 callersFunctionunitwise_norm
(x, norm_type=2.0)
timm/utils/agc.py:21
↓ 2 callersMethodupdate_slow
(self, group)
timm/optim/lookahead.py:29
↓ 2 callersFunctionwindow_partition
Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)
timm/models/swin_transformer.py:88
↓ 1 callersFunctionT5Trainer
( dataframe, args, )
main.py:54
↓ 1 callersMethod__init__
(self, config, embed_tokens=None, patch_size=None)
model.py:25
↓ 1 callersMethod__init__
(self, model, decay=0.9999, device='', resume='')
timm/utils/model_ema.py:37
↓ 1 callersMethod__init__
(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0)
timm/optim/radam.py:12
↓ 1 callersMethod__init__
(self, loader, mean=IMAGENET_DEFAULT_MEAN, std=IMAGENET_DEF
timm/data/loader.py:56
↓ 1 callersMethod__init__
(self, tf: tarfile.TarFile = None, ti: tarfile.TarInfo = None)
timm/data/parsers/parser_image_in_tar.py:33
↓ 1 callersMethod__init__
(self, block_args, num_classes=1000, in_chans=3, stem_size=16, num_features=1280, head_bias=True,
timm/models/mobilenetv3.py:92
↓ 1 callersMethod__init__
(self, in_chans=3, num_classes=1000, global_pool='avg', output_stride=32, initial_chs=16, fin
timm/models/rexnet.py:145
↓ 1 callersMethod__init__
(self, inplanes, planes, stride=1, downsample=None, cardinality=1, base_width=64, sk_kwargs=N
timm/models/sknet.py:49
↓ 1 callersMethod__init__
( self, cfg: List[Any], num_classes: int = 1000, in_chans: int = 3, ou
timm/models/vgg.py:83
↓ 1 callersMethod__init__
(self, block_args, num_classes=1000, num_features=1280, in_chans=3, stem_size=32, fix_stem=False,
timm/models/efficientnet.py:416
↓ 1 callersMethod__init__
(self)
timm/loss/cross_entropy.py:31
↓ 1 callersMethod__init__
(self, gamma_neg=4, gamma_pos=1, clip=0.05, eps=1e-8, disable_torch_grad_focal_loss=False)
timm/loss/asymmetric_loss.py:6
↓ 1 callersMethod__iter__
(self)
timm/data/loader.py:78
↓ 1 callersMethod__setstate__
(self, state)
timm/optim/radam.py:17
↓ 1 callersMethod_apply_basic
(self, img, mixing_weights, m)
timm/data/auto_augment.py:748
↓ 1 callersMethod_apply_blended
(self, img, mixing_weights, m)
timm/data/auto_augment.py:732
↓ 1 callersMethod_apply_noise
(self, epoch)
timm/scheduler/plateau_lr.py:93
↓ 1 callersMethod_approx_sq_grad
(self, exp_avg_sq_row, exp_avg_sq_col)
timm/optim/adafactor.py:76
↓ 1 callersFunction_at_least_x_are_equal
At least `x` of `a` and `b` `Tensors` are equal.
timm/data/tf_preprocessing.py:84
↓ 1 callersFunction_block_cfg
(width_mult=1.0, depth_mult=1.0, initial_chs=16, final_chs=180, se_ratio=0., ch_div=1)
timm/models/rexnet.py:99
↓ 1 callersFunction_build_blocks
( block_cfg, prev_chs, width_mult, ch_div=1, act_layer='swish', dw_act_layer='relu6', drop_path_rate=0
timm/models/rexnet.py:119
↓ 1 callersMethod_build_tf_graph
(self)
timm/data/tf_preprocessing.py:214
↓ 1 callersMethod_calc_blended_weights
(self, ws, m)
timm/data/auto_augment.py:722
↓ 1 callersFunction_cfg_to_stage_args
(cfg, curr_stride=2, output_stride=32, drop_path_rate=0.)
timm/models/cspnet.py:303
↓ 1 callersMethod_check_branches
(self, num_branches, blocks, num_blocks, num_inchannels, num_channels)
timm/models/hrnet.py:406
↓ 1 callersMethod_cleanup_checkpoints
(self, trim=0)
timm/utils/checkpoint_saver.py:118
↓ 1 callersMethod_cosine_similarity
(self, x, y, eps, view_func)
timm/optim/adamp.py:29
↓ 1 callersMethod_cosine_similarity
(self, x, y, eps, view_func)
timm/optim/sgdp.py:29
↓ 1 callersFunction_create_gluon_xception
(variant, pretrained=False, **kwargs)
timm/models/gluon_xception.py:234
↓ 1 callersMethod_create_hook
(self, hook_fn)
timm/utils/model.py:64
↓ 1 callersFunction_create_inception_v4
(variant, pretrained=False, **kwargs)
timm/models/inception_v4.py:306
↓ 1 callersFunction_create_nasnet
(variant, pretrained=False, **kwargs)
timm/models/nasnet.py:554
↓ 1 callersFunction_create_pnasnet
(variant, pretrained=False, **kwargs)
timm/models/pnasnet.py:335
↓ 1 callersFunction_decode_and_random_crop
Make a random crop of image_size.
timm/data/tf_preprocessing.py:91
↓ 1 callersFunction_decode_block_str
Decode block definition string Gets a list of block arg (dicts) through a string notation of arguments. E.g. ir_r2_k3_s2_e1_i32_o16_se0.25_n
timm/models/efficientnet_builder.py:76
↓ 1 callersFunction_extract_tarinfo
(tf: tarfile.TarFile, parent_info: Dict, extensions=IMG_EXTENSIONS)
timm/data/parsers/parser_image_in_tar.py:42
↓ 1 callersFunction_flip
Random horizontal image flip.
timm/data/tf_preprocessing.py:134
↓ 1 callersMethod_forward
(self, x)
timm/models/inception_v3.py:69
↓ 1 callersMethod_forward
(self, x)
timm/models/inception_v3.py:102
↓ 1 callersMethod_forward
(self, x)
timm/models/inception_v3.py:140
↓ 1 callersMethod_forward
(self, x)
timm/models/inception_v3.py:178
↓ 1 callersMethod_forward
(self, x)
timm/models/inception_v3.py:215
↓ 1 callersFunction_gen_fbnetc
FBNet-C Paper: https://arxiv.org/abs/1812.03443 Ref Impl: https://github.com/facebookresearch/maskrcnn-benchmark/blob/master/maskrcn
timm/models/efficientnet.py:693
← previousnext →201–300 of 1,823, ranked by callers