Upload VideoMAEForPreTraining
Browse files- config.json +29 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VideoMAEForPreTraining"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"decoder_hidden_size": 384,
|
| 7 |
+
"decoder_intermediate_size": 1536,
|
| 8 |
+
"decoder_num_attention_heads": 6,
|
| 9 |
+
"decoder_num_hidden_layers": 4,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.0,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"image_size": 224,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"model_type": "videomae",
|
| 18 |
+
"norm_pix_loss": true,
|
| 19 |
+
"num_attention_heads": 12,
|
| 20 |
+
"num_channels": 3,
|
| 21 |
+
"num_frames": 16,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"patch_size": 16,
|
| 24 |
+
"qkv_bias": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.22.0.dev0",
|
| 27 |
+
"tubelet_size": 2,
|
| 28 |
+
"use_mean_pooling": false
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e0c3f4bc73c6d287b96c30975b43d60c9fc004c548150f252278f1becd89a7d
|
| 3 |
+
size 376924301
|