Upload folder using huggingface_hub
Browse files- checkpoint-1625/config.json +44 -0
- checkpoint-1625/optimizer.pt +3 -0
- checkpoint-1625/preprocessor_config.json +22 -0
- checkpoint-1625/pytorch_model.bin +3 -0
- checkpoint-1625/rng_state.pth +3 -0
- checkpoint-1625/scheduler.pt +3 -0
- checkpoint-1625/trainer_state.json +262 -0
- checkpoint-1625/training_args.bin +3 -0
- config.json +44 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
checkpoint-1625/config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "captain america",
|
| 13 |
+
"1": "black widow",
|
| 14 |
+
"2": "spider-man",
|
| 15 |
+
"3": "thanos",
|
| 16 |
+
"4": "ironman",
|
| 17 |
+
"5": "hulk",
|
| 18 |
+
"6": "loki",
|
| 19 |
+
"7": "doctor strange"
|
| 20 |
+
},
|
| 21 |
+
"image_size": 224,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"black widow": 1,
|
| 26 |
+
"captain america": 0,
|
| 27 |
+
"doctor strange": 7,
|
| 28 |
+
"hulk": 5,
|
| 29 |
+
"ironman": 4,
|
| 30 |
+
"loki": 6,
|
| 31 |
+
"spider-man": 2,
|
| 32 |
+
"thanos": 3
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-12,
|
| 35 |
+
"model_type": "vit",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"patch_size": 16,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.33.2"
|
| 44 |
+
}
|
checkpoint-1625/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b345098f665700b81893bb66d9d68f1980211c28a99b0e105e2e7458c640d55
|
| 3 |
+
size 686605317
|
checkpoint-1625/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-1625/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d1ebe5dd796a210fc0c1a4310776fa3fbbe73c66e3e5fc0814dc0484ba1634e
|
| 3 |
+
size 343287149
|
checkpoint-1625/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f2ba30b3591717f221afc5194b792c02ed70209392963ed75a90349acb47372
|
| 3 |
+
size 14575
|
checkpoint-1625/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:243df8b6efa19924826226c8ec42920036fcb43b329f0d3067509873bcf45cb5
|
| 3 |
+
size 627
|
checkpoint-1625/trainer_state.json
ADDED
|
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9350796341896057,
|
| 3 |
+
"best_model_checkpoint": "marvel_heroes_image_detection/checkpoint-1625",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1625,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.2514506769825919,
|
| 14 |
+
"eval_loss": 2.031909227371216,
|
| 15 |
+
"eval_runtime": 10.5044,
|
| 16 |
+
"eval_samples_per_second": 49.218,
|
| 17 |
+
"eval_steps_per_second": 6.188,
|
| 18 |
+
"step": 65
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.48549323017408125,
|
| 23 |
+
"eval_loss": 1.9182429313659668,
|
| 24 |
+
"eval_runtime": 10.4516,
|
| 25 |
+
"eval_samples_per_second": 49.466,
|
| 26 |
+
"eval_steps_per_second": 6.219,
|
| 27 |
+
"step": 130
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.6092843326885881,
|
| 32 |
+
"eval_loss": 1.7771351337432861,
|
| 33 |
+
"eval_runtime": 10.5159,
|
| 34 |
+
"eval_samples_per_second": 49.164,
|
| 35 |
+
"eval_steps_per_second": 6.181,
|
| 36 |
+
"step": 195
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.6634429400386848,
|
| 41 |
+
"eval_loss": 1.622236967086792,
|
| 42 |
+
"eval_runtime": 10.6077,
|
| 43 |
+
"eval_samples_per_second": 48.738,
|
| 44 |
+
"eval_steps_per_second": 6.128,
|
| 45 |
+
"step": 260
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.6808510638297872,
|
| 50 |
+
"eval_loss": 1.4729310274124146,
|
| 51 |
+
"eval_runtime": 10.7259,
|
| 52 |
+
"eval_samples_per_second": 48.201,
|
| 53 |
+
"eval_steps_per_second": 6.06,
|
| 54 |
+
"step": 325
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.6847195357833655,
|
| 59 |
+
"eval_loss": 1.3464027643203735,
|
| 60 |
+
"eval_runtime": 10.5753,
|
| 61 |
+
"eval_samples_per_second": 48.887,
|
| 62 |
+
"eval_steps_per_second": 6.146,
|
| 63 |
+
"step": 390
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7021276595744681,
|
| 68 |
+
"eval_loss": 1.2494332790374756,
|
| 69 |
+
"eval_runtime": 10.6814,
|
| 70 |
+
"eval_samples_per_second": 48.402,
|
| 71 |
+
"eval_steps_per_second": 6.085,
|
| 72 |
+
"step": 455
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.69,
|
| 76 |
+
"learning_rate": 8.59375e-06,
|
| 77 |
+
"loss": 1.5805,
|
| 78 |
+
"step": 500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 8.0,
|
| 82 |
+
"eval_accuracy": 0.7176015473887815,
|
| 83 |
+
"eval_loss": 1.1711503267288208,
|
| 84 |
+
"eval_runtime": 10.4186,
|
| 85 |
+
"eval_samples_per_second": 49.623,
|
| 86 |
+
"eval_steps_per_second": 6.239,
|
| 87 |
+
"step": 520
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 9.0,
|
| 91 |
+
"eval_accuracy": 0.723404255319149,
|
| 92 |
+
"eval_loss": 1.1158246994018555,
|
| 93 |
+
"eval_runtime": 10.4118,
|
| 94 |
+
"eval_samples_per_second": 49.655,
|
| 95 |
+
"eval_steps_per_second": 6.243,
|
| 96 |
+
"step": 585
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 10.0,
|
| 100 |
+
"eval_accuracy": 0.723404255319149,
|
| 101 |
+
"eval_loss": 1.0686367750167847,
|
| 102 |
+
"eval_runtime": 10.392,
|
| 103 |
+
"eval_samples_per_second": 49.75,
|
| 104 |
+
"eval_steps_per_second": 6.255,
|
| 105 |
+
"step": 650
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 11.0,
|
| 109 |
+
"eval_accuracy": 0.7137330754352031,
|
| 110 |
+
"eval_loss": 1.0390865802764893,
|
| 111 |
+
"eval_runtime": 10.4138,
|
| 112 |
+
"eval_samples_per_second": 49.646,
|
| 113 |
+
"eval_steps_per_second": 6.242,
|
| 114 |
+
"step": 715
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 12.0,
|
| 118 |
+
"eval_accuracy": 0.7156673114119922,
|
| 119 |
+
"eval_loss": 1.0162136554718018,
|
| 120 |
+
"eval_runtime": 10.4356,
|
| 121 |
+
"eval_samples_per_second": 49.542,
|
| 122 |
+
"eval_steps_per_second": 6.229,
|
| 123 |
+
"step": 780
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 13.0,
|
| 127 |
+
"eval_accuracy": 0.7156673114119922,
|
| 128 |
+
"eval_loss": 0.993504524230957,
|
| 129 |
+
"eval_runtime": 10.4092,
|
| 130 |
+
"eval_samples_per_second": 49.668,
|
| 131 |
+
"eval_steps_per_second": 6.244,
|
| 132 |
+
"step": 845
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 14.0,
|
| 136 |
+
"eval_accuracy": 0.7040618955512572,
|
| 137 |
+
"eval_loss": 0.9884597659111023,
|
| 138 |
+
"eval_runtime": 10.3867,
|
| 139 |
+
"eval_samples_per_second": 49.775,
|
| 140 |
+
"eval_steps_per_second": 6.258,
|
| 141 |
+
"step": 910
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 15.0,
|
| 145 |
+
"eval_accuracy": 0.7137330754352031,
|
| 146 |
+
"eval_loss": 0.971124529838562,
|
| 147 |
+
"eval_runtime": 10.5321,
|
| 148 |
+
"eval_samples_per_second": 49.088,
|
| 149 |
+
"eval_steps_per_second": 6.172,
|
| 150 |
+
"step": 975
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 15.38,
|
| 154 |
+
"learning_rate": 7.031250000000001e-06,
|
| 155 |
+
"loss": 0.784,
|
| 156 |
+
"step": 1000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 16.0,
|
| 160 |
+
"eval_accuracy": 0.7156673114119922,
|
| 161 |
+
"eval_loss": 0.9606119990348816,
|
| 162 |
+
"eval_runtime": 10.3697,
|
| 163 |
+
"eval_samples_per_second": 49.857,
|
| 164 |
+
"eval_steps_per_second": 6.268,
|
| 165 |
+
"step": 1040
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 17.0,
|
| 169 |
+
"eval_accuracy": 0.7137330754352031,
|
| 170 |
+
"eval_loss": 0.9606834650039673,
|
| 171 |
+
"eval_runtime": 10.3723,
|
| 172 |
+
"eval_samples_per_second": 49.844,
|
| 173 |
+
"eval_steps_per_second": 6.267,
|
| 174 |
+
"step": 1105
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 18.0,
|
| 178 |
+
"eval_accuracy": 0.7195357833655706,
|
| 179 |
+
"eval_loss": 0.9507700204849243,
|
| 180 |
+
"eval_runtime": 10.5,
|
| 181 |
+
"eval_samples_per_second": 49.238,
|
| 182 |
+
"eval_steps_per_second": 6.191,
|
| 183 |
+
"step": 1170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 19.0,
|
| 187 |
+
"eval_accuracy": 0.7272727272727273,
|
| 188 |
+
"eval_loss": 0.9467002749443054,
|
| 189 |
+
"eval_runtime": 10.3715,
|
| 190 |
+
"eval_samples_per_second": 49.848,
|
| 191 |
+
"eval_steps_per_second": 6.267,
|
| 192 |
+
"step": 1235
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 20.0,
|
| 196 |
+
"eval_accuracy": 0.7117988394584139,
|
| 197 |
+
"eval_loss": 0.9470967054367065,
|
| 198 |
+
"eval_runtime": 10.3883,
|
| 199 |
+
"eval_samples_per_second": 49.767,
|
| 200 |
+
"eval_steps_per_second": 6.257,
|
| 201 |
+
"step": 1300
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 21.0,
|
| 205 |
+
"eval_accuracy": 0.7176015473887815,
|
| 206 |
+
"eval_loss": 0.9421167969703674,
|
| 207 |
+
"eval_runtime": 10.518,
|
| 208 |
+
"eval_samples_per_second": 49.154,
|
| 209 |
+
"eval_steps_per_second": 6.18,
|
| 210 |
+
"step": 1365
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 22.0,
|
| 214 |
+
"eval_accuracy": 0.7195357833655706,
|
| 215 |
+
"eval_loss": 0.9433531761169434,
|
| 216 |
+
"eval_runtime": 10.4467,
|
| 217 |
+
"eval_samples_per_second": 49.489,
|
| 218 |
+
"eval_steps_per_second": 6.222,
|
| 219 |
+
"step": 1430
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 23.0,
|
| 223 |
+
"eval_accuracy": 0.7253384912959381,
|
| 224 |
+
"eval_loss": 0.9400549530982971,
|
| 225 |
+
"eval_runtime": 10.764,
|
| 226 |
+
"eval_samples_per_second": 48.031,
|
| 227 |
+
"eval_steps_per_second": 6.039,
|
| 228 |
+
"step": 1495
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 23.08,
|
| 232 |
+
"learning_rate": 5.468750000000001e-06,
|
| 233 |
+
"loss": 0.4835,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 24.0,
|
| 238 |
+
"eval_accuracy": 0.7137330754352031,
|
| 239 |
+
"eval_loss": 0.9435180425643921,
|
| 240 |
+
"eval_runtime": 10.4222,
|
| 241 |
+
"eval_samples_per_second": 49.606,
|
| 242 |
+
"eval_steps_per_second": 6.237,
|
| 243 |
+
"step": 1560
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 25.0,
|
| 247 |
+
"eval_accuracy": 0.7330754352030948,
|
| 248 |
+
"eval_loss": 0.9350796341896057,
|
| 249 |
+
"eval_runtime": 10.8587,
|
| 250 |
+
"eval_samples_per_second": 47.612,
|
| 251 |
+
"eval_steps_per_second": 5.986,
|
| 252 |
+
"step": 1625
|
| 253 |
+
}
|
| 254 |
+
],
|
| 255 |
+
"logging_steps": 500,
|
| 256 |
+
"max_steps": 3250,
|
| 257 |
+
"num_train_epochs": 50,
|
| 258 |
+
"save_steps": 500,
|
| 259 |
+
"total_flos": 4.004613904280371e+18,
|
| 260 |
+
"trial_name": null,
|
| 261 |
+
"trial_params": null
|
| 262 |
+
}
|
checkpoint-1625/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:595ed5adb1763ac0ae330b132ea78dfc27c4a4ee91b83f1b5911e63655d1cf31
|
| 3 |
+
size 4027
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "captain america",
|
| 13 |
+
"1": "black widow",
|
| 14 |
+
"2": "spider-man",
|
| 15 |
+
"3": "thanos",
|
| 16 |
+
"4": "ironman",
|
| 17 |
+
"5": "hulk",
|
| 18 |
+
"6": "loki",
|
| 19 |
+
"7": "doctor strange"
|
| 20 |
+
},
|
| 21 |
+
"image_size": 224,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 3072,
|
| 24 |
+
"label2id": {
|
| 25 |
+
"black widow": 1,
|
| 26 |
+
"captain america": 0,
|
| 27 |
+
"doctor strange": 7,
|
| 28 |
+
"hulk": 5,
|
| 29 |
+
"ironman": 4,
|
| 30 |
+
"loki": 6,
|
| 31 |
+
"spider-man": 2,
|
| 32 |
+
"thanos": 3
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-12,
|
| 35 |
+
"model_type": "vit",
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"patch_size": 16,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.33.2"
|
| 44 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d1ebe5dd796a210fc0c1a4310776fa3fbbe73c66e3e5fc0814dc0484ba1634e
|
| 3 |
+
size 343287149
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:595ed5adb1763ac0ae330b132ea78dfc27c4a4ee91b83f1b5911e63655d1cf31
|
| 3 |
+
size 4027
|