blanchon commited on
Commit
5838c87
·
verified ·
1 Parent(s): efd9e47

Upload folder using huggingface_hub

Browse files
checkpoints/model.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757bea86d97f9e7ab434ebc1a074c4f9d457b0b24fb0d72d50ae3a6e08574914
3
+ size 258324601
clip/config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "clip-vit-large-patch14/",
3
+ "architectures": [
4
+ "CLIPModel"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "_name_or_path": "",
12
+ "add_cross_attention": false,
13
+ "architectures": null,
14
+ "attention_dropout": 0.0,
15
+ "bad_words_ids": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "dropout": 0.0,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "hidden_act": "quick_gelu",
30
+ "hidden_size": 768,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1"
34
+ },
35
+ "initializer_factor": 1.0,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "layer_norm_eps": 1e-05,
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "max_position_embeddings": 77,
48
+ "min_length": 0,
49
+ "model_type": "clip_text_model",
50
+ "no_repeat_ngram_size": 0,
51
+ "num_attention_heads": 12,
52
+ "num_beam_groups": 1,
53
+ "num_beams": 1,
54
+ "num_hidden_layers": 12,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": 1,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "projection_dim" : 768,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
+ "task_specific_params": null,
70
+ "temperature": 1.0,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.16.0.dev0",
79
+ "use_bfloat16": false,
80
+ "vocab_size": 49408
81
+ },
82
+ "text_config_dict": {
83
+ "hidden_size": 768,
84
+ "intermediate_size": 3072,
85
+ "num_attention_heads": 12,
86
+ "num_hidden_layers": 12,
87
+ "projection_dim": 768
88
+ },
89
+ "torch_dtype": "float32",
90
+ "transformers_version": null,
91
+ "vision_config": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_dropout": 0.0,
96
+ "bad_words_ids": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "quick_gelu",
111
+ "hidden_size": 1024,
112
+ "id2label": {
113
+ "0": "LABEL_0",
114
+ "1": "LABEL_1"
115
+ },
116
+ "image_size": 224,
117
+ "initializer_factor": 1.0,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 4096,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-05,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "clip_vision_model",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 16,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_hidden_layers": 24,
136
+ "num_return_sequences": 1,
137
+ "output_attentions": false,
138
+ "output_hidden_states": false,
139
+ "output_scores": false,
140
+ "pad_token_id": null,
141
+ "patch_size": 14,
142
+ "prefix": null,
143
+ "problem_type": null,
144
+ "projection_dim" : 768,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "sep_token_id": null,
151
+ "task_specific_params": null,
152
+ "temperature": 1.0,
153
+ "tie_encoder_decoder": false,
154
+ "tie_word_embeddings": true,
155
+ "tokenizer_class": null,
156
+ "top_k": 50,
157
+ "top_p": 1.0,
158
+ "torch_dtype": null,
159
+ "torchscript": false,
160
+ "transformers_version": "4.16.0.dev0",
161
+ "use_bfloat16": false
162
+ },
163
+ "vision_config_dict": {
164
+ "hidden_size": 1024,
165
+ "intermediate_size": 4096,
166
+ "num_attention_heads": 16,
167
+ "num_hidden_layers": 24,
168
+ "patch_size": 14,
169
+ "projection_dim": 768
170
+ }
171
+ }
clip/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
clip/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": 224,
3
+ "do_center_crop": true,
4
+ "do_normalize": true,
5
+ "do_resize": true,
6
+ "feature_extractor_type": "CLIPFeatureExtractor",
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "resample": 3,
18
+ "size": 224
19
+ }
clip/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1a17cdbe0f36fec524f5cafb1c261ea3bbbc13e346e0f74fc9eb0460dedd0d3
3
+ size 1710671599
clip/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
clip/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
clip/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": {
3
+ "content": "<|endoftext|>",
4
+ "single_word": false,
5
+ "lstrip": false,
6
+ "rstrip": false,
7
+ "normalized": true,
8
+ "__type": "AddedToken"
9
+ },
10
+ "bos_token": {
11
+ "content": "<|startoftext|>",
12
+ "single_word": false,
13
+ "lstrip": false,
14
+ "rstrip": false,
15
+ "normalized": true,
16
+ "__type": "AddedToken"
17
+ },
18
+ "eos_token": {
19
+ "content": "<|endoftext|>",
20
+ "single_word": false,
21
+ "lstrip": false,
22
+ "rstrip": false,
23
+ "normalized": true,
24
+ "__type": "AddedToken"
25
+ },
26
+ "pad_token": "<|endoftext|>",
27
+ "add_prefix_space": false,
28
+ "errors": "replace",
29
+ "do_lower_case": true,
30
+ "name_or_path": "openai/clip-vit-base-patch32",
31
+ "model_max_length": 77,
32
+ "special_tokens_map_file": "./special_tokens_map.json",
33
+ "tokenizer_class": "CLIPTokenizer"
34
+ }
clip/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
glove/our_vab_data.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ed9b73ee5bc5ab683661c132b9f98fe305672dffdf70ceeac1bc447543d668
3
+ size 10077728
glove/our_vab_idx.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85dce83d2c27a92bb94bb51dc1f55a04fcaa328c359d23eccf648e296c16493
3
+ size 79811
glove/our_vab_words.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac88da1be6f00d36b72b88c9745c8ac35a94a7bd6ccf1fa3bab380faf8c2e0d
3
+ size 67470
humanml3d/Mean.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e136555dab04c94a129d446c26e6b9939cbf045fbf77bcf5462c1fb5a2001c
3
+ size 1180
humanml3d/Std.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6565a65ed9b31e23c328829a309e1c482be8b85fd23b43d65451a9b19a917f40
3
+ size 1180
t2m/Comp_v6_KLD01/._meta ADDED
Binary file (210 Bytes). View file
 
t2m/Comp_v6_KLD01/._model ADDED
Binary file (210 Bytes). View file
 
t2m/Comp_v6_KLD01/._opt.txt ADDED
Binary file (210 Bytes). View file
 
t2m/Comp_v6_KLD01/meta/._mean.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41de7e93b56e3c1128730c898714eb005709a36721829af41ccbf5bdeacf60c7
3
+ size 210
t2m/Comp_v6_KLD01/meta/._std.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07031e2d57d50c576964e4401c42d24be56f635aba6bc1ba8fafb7423f3535d0
3
+ size 210
t2m/Comp_v6_KLD01/meta/mean.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bdb5ba69a3a9e34d71990db15bc535ebc024c8d95ddb5574196f96058faa7d3
3
+ size 2232
t2m/Comp_v6_KLD01/meta/std.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5f7d60301c9465972fc225f8ad0ee8f957e7720431189123eb6d15873a9557
3
+ size 2232
t2m/Comp_v6_KLD01/model/._latest.tar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdd1c83c884cb21a02b7c52b42f9c0e6d620e04f107617634cd88959fde095bf
3
+ size 210
t2m/Comp_v6_KLD01/model/latest.tar ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc213a109b257c3da93e60f39cf364c8e93f808f6c22b403579398423397a67b
3
+ size 425081837
t2m/Comp_v6_KLD01/opt.txt ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ------------ Options -------------
2
+ batch_size: 32
3
+ checkpoints_dir: ./checkpoints
4
+ dataset_name: t2m
5
+ decomp_name: Decomp_SP001_SM001_H512
6
+ dim_att_vec: 512
7
+ dim_dec_hidden: 1024
8
+ dim_movement2_dec_hidden: 512
9
+ dim_movement_dec_hidden: 512
10
+ dim_movement_enc_hidden: 512
11
+ dim_movement_latent: 512
12
+ dim_msd_hidden: 512
13
+ dim_pos_hidden: 1024
14
+ dim_pri_hidden: 1024
15
+ dim_seq_de_hidden: 512
16
+ dim_seq_en_hidden: 512
17
+ dim_text_hidden: 512
18
+ dim_z: 128
19
+ early_stop_count: 3
20
+ estimator_mod: bigru
21
+ eval_every_e: 5
22
+ feat_bias: 5
23
+ fixed_steps: 5
24
+ gpu_id: 3
25
+ input_z: False
26
+ is_continue: True
27
+ is_train: True
28
+ lambda_fake: 10
29
+ lambda_gan_l: 0.1
30
+ lambda_gan_mt: 0.1
31
+ lambda_gan_mv: 0.1
32
+ lambda_kld: 0.01
33
+ lambda_rec: 1
34
+ lambda_rec_init: 1
35
+ lambda_rec_mot: 1
36
+ lambda_rec_mov: 1
37
+ log_every: 50
38
+ lr: 0.0002
39
+ max_sub_epoch: 50
40
+ max_text_len: 20
41
+ n_layers_dec: 1
42
+ n_layers_msd: 2
43
+ n_layers_pos: 1
44
+ n_layers_pri: 1
45
+ n_layers_seq_de: 2
46
+ n_layers_seq_en: 1
47
+ name: Comp_v6_KLD01
48
+ num_experts: 4
49
+ save_every_e: 10
50
+ save_latest: 500
51
+ text_enc_mod: bigru
52
+ tf_ratio: 0.4
53
+ unit_length: 4
54
+ -------------- End ----------------