diff --git a/config.json b/config.json new file mode 100644 index 0000000..fdd55f1 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "architectures": [ + "VideoMAEForVideoClassification" + ], + "attention_probs_dropout_prob": 0.1, + "decoder_hidden_size": 384, + "decoder_intermediate_size": 1536, + "decoder_num_attention_heads": 6, + "decoder_num_hidden_layers": 4, + "hidden_act": "gelu", + "hidden_dropout_prob": 0.1, + "hidden_size": 32, + "image_size": 10, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-12, + "model_type": "videomae", + "norm_pix_loss": true, + "num_attention_heads": 4, + "num_channels": 3, + "num_frames": 2, + "num_hidden_layers": 5, + "patch_size": 2, + "qkv_bias": true, + "torch_dtype": "float32", + "transformers_version": "4.25.0.dev0", + "tubelet_size": 2, + "use_mean_pooling": true +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..79149fe --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,26 @@ +{ + "crop_size": { + "height": 10, + "width": 10 + }, + "do_center_crop": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "VideoMAEImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "resample": 2, + "rescale_factor": 0.00392156862745098, + "size": { + "shortest_edge": 10 + } +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..2f11748 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4340d566c60dadffec0a891eed013d4a59454d5d1ea99fbf4edf1ba6d8a0c1 +size 164964