first commit

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,148 @@
+---
+pipeline_tag: image-to-text
+tags:
+- image-captioning
+languages:
+- en
+license: bsd-3-clause
+---
+
+# BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
+
+Model card for image captioning pretrained on COCO dataset - base architecture (with ViT large backbone).
+
+| ![BLIP.gif](https://cdn-uploads.huggingface.co/production/uploads/1670928184033-62441d1d9fdefb55a0b7d12c.gif) |
+|:--:|
+| <b> Pull figure from BLIP official repo | Image source: https://github.com/salesforce/BLIP </b>|
+
+## TL;DR
+
+Authors from the [paper](https://arxiv.org/abs/2201.12086) write in the abstract:
+
+*Vision-Language Pre-training (VLP) has advanced the performance for many vision-language tasks. However, most existing pre-trained models only excel in either understanding-based tasks or generation-based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image-text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision-language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state-of-the-art results on a wide range of vision-language tasks, such as image-text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to videolanguage tasks in a zero-shot manner. Code, models, and datasets are released.*
+
+## Usage
+
+You can use this model for conditional and un-conditional image captioning
+
+### Using the Pytorch model
+
+#### Running the model on CPU
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+
+img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+# conditional image captioning
+text = "a photography of"
+inputs = processor(raw_image, text, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+```
+</details>
+
+#### Running the model on GPU
+
+##### In full precision 
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large").to("cuda")
+
+img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+# conditional image captioning
+text = "a photography of"
+inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt").to("cuda")
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+```
+</details>
+
+##### In half precision (`float16`)
+
+<details>
+<summary> Click to expand </summary>
+
+```python
+import torch
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", torch_dtype=torch.float16).to("cuda")
+
+img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
+raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
+
+# conditional image captioning
+text = "a photography of"
+inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+# >>> a photography of a woman and her dog
+
+# unconditional image captioning
+inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
+
+out = model.generate(**inputs)
+print(processor.decode(out[0], skip_special_tokens=True))
+>>> a woman sitting on the beach with her dog
+```
+</details>
+
+## BibTex and citation info
+
+```
+@misc{https://doi.org/10.48550/arxiv.2201.12086,
+  doi = {10.48550/ARXIV.2201.12086},
+  
+  url = {https://arxiv.org/abs/2201.12086},
+  
+  author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven},
+  
+  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
+  
+  title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation},
+  
+  publisher = {arXiv},
+  
+  year = {2022},
+  
+  copyright = {Creative Commons Attribution 4.0 International}
+}
+```

config.json

@@ -0,0 +1,170 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 30522,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_hidden_size": 1024,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "blip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": 102,
+    "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": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30524
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "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": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": "blip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "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": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "BlipImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "BlipProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  },
+  "size_divisor": 32
+}

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 +1,21 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "Salesforce/blip-image-captioning-large",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "processor_class": "BlipProcessor",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ]
+}