Upload 9 files

README.md

@@ -1,3 +1,66 @@
 ---
 license: apache-2.0
+tags:
+- image-captioning
+languages:
+- en
+pipeline_tag: image-to-text
+datasets:
+- michelecafagna26/hl
+language:
+- en
+metrics:
+- sacrebleu
+- rouge
+library_name: transformers
 ---
+## GIT-base fine-tuned for Image Captioning on High-Level descriptions of Actions
+
+[GIT](https://arxiv.org/abs/2205.14100) base trained on the [HL dataset](https://huggingface.co/datasets/michelecafagna26/hl) for **action generation of images**
+
+## Model fine-tuning 🏋️‍
+
+Trained for a maximum of 10 epochs using a
+lr:  5e−5,
+Adam optimizer,
+half-precision (fp16)
+
+## Test set metrics 🧾
+
+    | Cider  | SacreBLEU  | Rouge-L|
+    |--------|------------|--------|
+    | 110.63 |    15.21   |  30.45 |
+
+## Model in Action 🚀
+
+```python
+import requests
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForCausalLM
+
+processor = AutoProcessor.from_pretrained("git-base-captioning-ft-hl-actions")
+model = AutoModelForCausalLM.from_pretrained("git-base-captioning-ft-hl-actions").to("cuda")
+
+img_url = 'https://datasets-server.huggingface.co/assets/michelecafagna26/hl/--/default/train/0/image/image.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+
+inputs = processor(raw_image, return_tensors="pt").to("cuda")
+pixel_values = inputs.pixel_values
+
+generated_ids = model.generate(pixel_values=pixel_values, max_length=50,
+            do_sample=True,
+            top_k=120,
+            top_p=0.9,
+            early_stopping=True,
+            num_return_sequences=1)
+
+processor.batch_decode(generated_ids, skip_special_tokens=True)
+
+>>>
+```
+
+## BibTex and citation info
+
+```BibTeX
+```

config.json

@@ -0,0 +1,107 @@
+{
+  "_commit_hash": "1f7fe8444292beb4a259e3a5b6eba440cd5999d4",
+  "_name_or_path": "microsoft/git-base",
+  "architectures": [
+    "GitForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 101,
+  "classifier_dropout": null,
+  "eos_token_id": 102,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "git",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "num_image_with_embedding": null,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_cache": true,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "git_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.30.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.2"
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "GitProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f3857fe328f1130375e1902b2aefb88ea6dacc11c1d9340d584e0565411719
+size 706594713

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "processor_class": "GitProcessor",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}