Update README.md

README.md

@@ -7,197 +7,130 @@ base_model: Qwen/Qwen-VL-Chat
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-
+- LoRA: wdtag -> long caption.
 
 ## Model Details
 
+- Finetuned.
+
 ### Model Description
 
 <!-- Provide a longer summary of what this model is. -->
 
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
+- **Developed by:** cella]
+- **Model type:** LoRA
+- **Language(s) (NLP):** Eng
+- **License:** Tongyi Qianwen LICENSE
+- **Finetuned from model [optional]:** Qwen-VL-Chat
+- 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure 
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
 
+### Model Load
+```
+LoRA_DIR = "/path-to-LoRA-dir"
+
+if OPTION_VLM_METHOD == 'qwen_chat_LoRA':
+        from peft import AutoPeftModelForCausalLM
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+        from transformers.generation import GenerationConfig
+        import torch
+        torch.manual_seed(1234)
+
+        # Note: The default behavior now has injection attack prevention off.
+        tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-VL-Chat", trust_remote_code=True)
+        \
+        # use cuda device
+        model = AutoPeftModelForCausalLM.from_pretrained(
+                LoRA_DIR, # path to the output directory
+                device_map="auto",
+                trust_remote_code=True
+        ).eval()
+
+        # Specify hyperparameters for generation (No need to do this if you are using transformers>=4.32.0)
+        model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-VL-Chat", trust_remote_code=True)
+        
+else:
+    print("skipped.")
+```
+
+### Captioning
+```
+if OPTION_VLM_METHOD == 'qwen_chat':
+    from PIL import Image
+    from langdetect import detect
+    import string
+    import re
+
+    COMMON_QUERY = 'What is in tha image? Briefly describe the overall, in English'
+    MORE_QUERY = 'What is in tha image? Describe the overall in detail, in English'
+    LESS_QUERY = 'What is in tha image? Briefly summerize the description, in English'
+
+    for image in dataset.images:       
+        img_name = os.path.basename(image.path)
+        img_name = os.path.splitext(img_name)[0]
+
+        # すでにアウトプットフォルダに同名のtxtファイルが存在する場合はスキップ
+        if OPTION_SKIP_EXISTING and os.path.exists(os.path.join(output_dir_VLM, img_name + '.txt')):
+            clear_output(True)
+            print("skipped: ", image.path)
+            continue
+
+        query = tokenizer.from_list_format([
+            {'image': image.path },
+            {'text': 'Make description using following words' + ', '.join(image.captions).replace('_', ' ') },
+        ])
+        response, history = model.chat(tokenizer, query=query, history=None)
+            
+        # ASCIIチェック、言語チェック、長さチェック
+        retry_count = 0
+        while not is_ascii(response) or not is_english(response) or not is_sufficient_length(response) or not is_over_length(response):
+            clear_output(True)
+            retry_count +=1
+            print("Retry count:", retry_count)
+            if retry_count >= 25 and is_ascii(response):
+                break
+            if not is_sufficient_length(response):
+                print("Too short. Retry...")
+                query = tokenizer.from_list_format([
+                    {'image': image.path },
+                    {'text': MORE_QUERY },
+                ])
+            if not is_over_length(response):
+                print("Too long. Retry...")
+                query = tokenizer.from_list_format([
+                    {'image': image.path },
+                    {'text': LESS_QUERY },
+                ])
+            if retry_count % 5 == 0:
+                history = None
+                query = tokenizer.from_list_format([
+                    {'image': image.path },
+                    {'text': COMMON_QUERY },
+                ])
+            response, history = model.chat(tokenizer, query=query, history=history)
+            
+        response = remove_fixed_patterns(response)
+
+        if OPTION_SAVE_TAGS:
+            # タグを保存
+            with open(os.path.join(output_dir_VLM, img_name + '.txt'), 'w') as file:
+                file.write(response)
+
+        image.captions = response
+
+        clear_output(True)
+
+        print("Saved for ", image.path, ": ", response)
+        
+        #画像を表示
+        img = Image.open(image.path)
+        plt.imshow(np.asarray(img))
+        plt.show()
+        
+else:
+    print("skipped.")
+```
 
 ### Framework versions