Training in progress, epoch 0
Browse files- config.json +48 -0
- model.safetensors +3 -0
- preprocessor_config.json +44 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vivit-b-16x2-kinetics400",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"VivitForVideoClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"hidden_act": "gelu_fast",
|
| 8 |
+
"hidden_dropout_prob": 0.0,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "Anger",
|
| 12 |
+
"1": "Disgust",
|
| 13 |
+
"2": "Happy",
|
| 14 |
+
"3": "Neutral",
|
| 15 |
+
"4": "Sad",
|
| 16 |
+
"5": "Surprise"
|
| 17 |
+
},
|
| 18 |
+
"image_size": 224,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Anger": 0,
|
| 23 |
+
"Disgust": 1,
|
| 24 |
+
"Happy": 2,
|
| 25 |
+
"Neutral": 3,
|
| 26 |
+
"Sad": 4,
|
| 27 |
+
"Surprise": 5
|
| 28 |
+
},
|
| 29 |
+
"layer_norm_eps": 1e-06,
|
| 30 |
+
"model_type": "vivit",
|
| 31 |
+
"num_attention_heads": 12,
|
| 32 |
+
"num_channels": 3,
|
| 33 |
+
"num_frames": 32,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"qkv_bias": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.39.0",
|
| 38 |
+
"tubelet_size": [
|
| 39 |
+
2,
|
| 40 |
+
16,
|
| 41 |
+
16
|
| 42 |
+
],
|
| 43 |
+
"video_size": [
|
| 44 |
+
32,
|
| 45 |
+
224,
|
| 46 |
+
224
|
| 47 |
+
]
|
| 48 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b68ffd2a2a884db820fa0d9f6d66a0077b056af43eefb322330f3b10437c6664
|
| 3 |
+
size 354627680
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"videos",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_center_crop",
|
| 8 |
+
"crop_size",
|
| 9 |
+
"do_rescale",
|
| 10 |
+
"rescale_factor",
|
| 11 |
+
"offset",
|
| 12 |
+
"do_normalize",
|
| 13 |
+
"image_mean",
|
| 14 |
+
"image_std",
|
| 15 |
+
"return_tensors",
|
| 16 |
+
"data_format",
|
| 17 |
+
"input_data_format"
|
| 18 |
+
],
|
| 19 |
+
"crop_size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
},
|
| 23 |
+
"do_center_crop": true,
|
| 24 |
+
"do_normalize": true,
|
| 25 |
+
"do_rescale": true,
|
| 26 |
+
"do_resize": true,
|
| 27 |
+
"image_mean": [
|
| 28 |
+
0.5,
|
| 29 |
+
0.5,
|
| 30 |
+
0.5
|
| 31 |
+
],
|
| 32 |
+
"image_processor_type": "VivitImageProcessor",
|
| 33 |
+
"image_std": [
|
| 34 |
+
0.5,
|
| 35 |
+
0.5,
|
| 36 |
+
0.5
|
| 37 |
+
],
|
| 38 |
+
"offset": true,
|
| 39 |
+
"resample": 2,
|
| 40 |
+
"rescale_factor": 0.00784313725490196,
|
| 41 |
+
"size": {
|
| 42 |
+
"shortest_edge": 224
|
| 43 |
+
}
|
| 44 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:712ad85010cef7a120cc137c7b99821343e53aa636cbd6cba14f716a5fd2c653
|
| 3 |
+
size 4984
|