Model save

README.md

@@ -0,0 +1,49 @@
+---
+library_name: transformers
+license: mit
+base_model: google/vivit-b-16x2-kinetics400
+tags:
+- generated_from_trainer
+model-index:
+- name: vivit-b-16x2-kinetics400-finetuned-cricket_shot_detection_NEW_1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vivit-b-16x2-kinetics400-finetuned-cricket_shot_detection_NEW_1
+
+This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 5800
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 1.13.1+cu117
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "google/vivit-b-16x2-kinetics400",
+  "architectures": [
+    "VivitForVideoClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "cover",
+    "1": "defence",
+    "2": "flick",
+    "3": "hook",
+    "4": "lofted",
+    "5": "pull"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "cover": 0,
+    "defence": 1,
+    "flick": 2,
+    "hook": 3,
+    "lofted": 4,
+    "pull": 5
+  },
+  "layer_norm_eps": 1e-06,
+  "model_type": "vivit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_frames": 32,
+  "num_hidden_layers": 12,
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "tubelet_size": [
+    2,
+    16,
+    16
+  ],
+  "video_size": [
+    32,
+    224,
+    224
+  ]
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ced4ef594cd099c2be8f474481d73e23817843ab21da4d5b88c2fc895ae43d2
+size 354627680

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "VivitImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "offset": true,
+  "resample": 2,
+  "rescale_factor": 0.00784313725490196,
+  "size": {
+    "shortest_edge": 224
+  }
+}

runs/Jan07_19-59-43_5fdc108cd364/events.out.tfevents.1736280000.5fdc108cd364.1215.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87c002b58287662b9ed5cc1c8078a89c51316c0958ea1f754fe8547125ff634b
+size 11837

runs/Jan07_20-02-33_5fdc108cd364/events.out.tfevents.1736280165.5fdc108cd364.1215.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0809dcec5511ef619f70ba5598cca07cf33a321f98208f9792219a4a12ebe84
+size 4184

runs/Jan07_20-03-02_5fdc108cd364/events.out.tfevents.1736280191.5fdc108cd364.1215.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdfd58ae7f1f60dc53b66d595497f7cc1bdf92f739a8a565d4643aed2260a8d
+size 4184

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3949fedd6f71ba3fff2fa5660d708bc9b9355a45b89476dd6f069a996014b98
+size 4987