Training in progress, step 500
Browse files- config.json +47 -0
- model.safetensors +3 -0
- preprocessor_config.json +26 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "MCG-NJU/videomae-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VideoMAEForVideoClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"decoder_hidden_size": 384,
|
| 8 |
+
"decoder_intermediate_size": 1536,
|
| 9 |
+
"decoder_num_attention_heads": 6,
|
| 10 |
+
"decoder_num_hidden_layers": 4,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.0,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "left_eye",
|
| 16 |
+
"1": "left_mouth",
|
| 17 |
+
"2": "open_mouth",
|
| 18 |
+
"3": "right_eye",
|
| 19 |
+
"4": "right_mouth",
|
| 20 |
+
"5": "up_eyebrow"
|
| 21 |
+
},
|
| 22 |
+
"image_size": 224,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"left_eye": 0,
|
| 27 |
+
"left_mouth": 1,
|
| 28 |
+
"open_mouth": 2,
|
| 29 |
+
"right_eye": 3,
|
| 30 |
+
"right_mouth": 4,
|
| 31 |
+
"up_eyebrow": 5
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-12,
|
| 34 |
+
"model_type": "videomae",
|
| 35 |
+
"norm_pix_loss": true,
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_channels": 3,
|
| 38 |
+
"num_frames": 16,
|
| 39 |
+
"num_hidden_layers": 12,
|
| 40 |
+
"patch_size": 16,
|
| 41 |
+
"problem_type": "single_label_classification",
|
| 42 |
+
"qkv_bias": true,
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.45.0",
|
| 45 |
+
"tubelet_size": 2,
|
| 46 |
+
"use_mean_pooling": false
|
| 47 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5936cac405ce41648c994412454a367ae246774181f672d816c4f4db060cc9f8
|
| 3 |
+
size 344949680
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_normalize": true,
|
| 8 |
+
"do_rescale": true,
|
| 9 |
+
"do_resize": true,
|
| 10 |
+
"image_mean": [
|
| 11 |
+
0.485,
|
| 12 |
+
0.456,
|
| 13 |
+
0.406
|
| 14 |
+
],
|
| 15 |
+
"image_processor_type": "VideoMAEImageProcessor",
|
| 16 |
+
"image_std": [
|
| 17 |
+
0.229,
|
| 18 |
+
0.224,
|
| 19 |
+
0.225
|
| 20 |
+
],
|
| 21 |
+
"resample": 2,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"shortest_edge": 224
|
| 25 |
+
}
|
| 26 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:064298f0a8616c3119e4670e80a9a428f0649b19988b7f767ef859c93d872c40
|
| 3 |
+
size 5176
|