rename path for ChatRex

IDEA-Research · Nov 26, 2024 · 0d29204 · 0d29204
1 parent 40e6401
commit 0d29204
Show file tree

Hide file tree

Showing 7 changed files with 39 additions and 41 deletions.
diff --git a/README.md b/README.md
@@ -22,7 +22,7 @@
 ----
 
 # 1. Introduction 📚
-**TL;DR: ChatRex is a MLLM skilled in perception that can respond to questions while simultaneously grounding its answers to the referenced objects.**
+**TL;DR: ChatRex is an MLLM skilled in perception that can respond to questions while simultaneously grounding its answers to the referenced objects.**
 
 ChatRex is a Multimodal Large Language Model (MLLM) designed to seamlessly integrate fine-grained object perception and robust language understanding. By adopting a decoupled architecture with a retrieval-based approach for object detection and leveraging high-resolution visual inputs, ChatRex addresses key challenges in perception tasks. It is powered by the Rexverse-2M dataset with diverse image-region-text annotations. ChatRex can be applied to various scenarios requiring fine-grained perception, such as object detection, grounded conversation, grounded image captioning and region
 understanding.
@@ -45,16 +45,15 @@ pip install -v -e .
 
 ## 2.1 Download Pre-trained Models
 We provide model checkpoints for both the ***Universal Proposal Network (UPN)*** and the ***ChatRex model***. You can download the pre-trained models from the following links:
-- [UPN Checkpoint](https://drive.google)
+- [UPN Checkpoint](https://github.com/IDEA-Research/ChatRex/releases/download/upn-large/upn_large.pth)
 - [ChatRex-7B Checkpoint](https://huggingface.co/IDEA-Research/ChatRex-7B)
 
 Or you can also using the following command to download the pre-trained models:
 ```bash
 mkdir checkpoints
 mkdir checkpoints/upn
 # download UPN checkpoint
-wget -O checkpoints/upn/upn_large.pth https://drive.google.com/file/d/
-# download ChatRex checkpoint from huggingface IDEA-Research/ChatRex-7B
+wget -O checkpoints/upn/upn_large.pth https://github.com/IDEA-Research/ChatRex/releases/download/upn-large/upn_large.pth
 # Download ChatRex checkpoint from Hugging Face
 git lfs install
 git clone https://huggingface.co/IDEA-Research/ChatRex-7B checkpoints/chatrex
@@ -190,15 +189,15 @@ from chatrex.upn import UPNWrapper
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")
@@ -308,15 +307,15 @@ from chatrex.upn import UPNWrapper
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")
@@ -402,15 +401,15 @@ from chatrex.upn import UPNWrapper
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")
@@ -506,15 +505,15 @@ from chatrex.upn import UPNWrapper
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")

diff --git a/gradio_demos/chatrex_demo.py b/gradio_demos/chatrex_demo.py
@@ -10,15 +10,15 @@
 from chatrex.upn import UPNWrapper
 
 processor = AutoProcessor.from_pretrained(
-    "checkpoints/chatrex7b",
+    "IDEA-Research/ChatRex-7B",
     trust_remote_code=True,
     device_map="cuda",
 )
 
 print(f"loading chatrex model...")
 # load chatrex model
 model = AutoModelForCausalLM.from_pretrained(
-    "checkpoints/chatrex7b",
+    "IDEA-Research/ChatRex-7B",
     trust_remote_code=True,
     use_safetensors=True,
 ).to("cuda")

diff --git a/tests/test_chatrex_detection.py b/tests/test_chatrex_detection.py
@@ -8,15 +8,15 @@
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")

diff --git a/tests/test_chatrex_grounded_conversation.py b/tests/test_chatrex_grounded_conversation.py
@@ -8,15 +8,15 @@
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")

diff --git a/tests/test_chatrex_grounded_image_caption.py b/tests/test_chatrex_grounded_image_caption.py
@@ -8,15 +8,15 @@
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")

diff --git a/tests/test_chatrex_install.py b/tests/test_chatrex_install.py
@@ -4,39 +4,38 @@
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     # load the model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
-    ).to('cuda')
+    ).to("cuda")
 
     inputs = processor.process(
-        image=Image.open(
-                'tests/images/test_chatrex_install.jpg'
-            ),
+        image=Image.open("tests/images/test_chatrex_install.jpg"),
         question="Can you provide me with a brief description of <obj0>?",
-        bbox=[[73.88417,56.62228,227.69223,216.34338]] # box in xyxy format
+        bbox=[[73.88417, 56.62228, 227.69223, 216.34338]],  # box in xyxy format
     )
 
-
     inputs = {k: v.to("cuda") for k, v in inputs.items()}
 
     # perform inference
     gen_config = GenerationConfig(
-            max_new_tokens=512, 
-            do_sample=False,
-            eos_token_id=processor.tokenizer.eos_token_id,
-            pad_token_id=(
-                processor.tokenizer.pad_token_id
-                if processor.tokenizer.pad_token_id is not None
-                else processor.tokenizer.eos_token_id
-            ))
-    prediction = model.generate(inputs, gen_config=gen_config, tokenizer=processor.tokenizer)
-    print(f'prediction:', prediction)
-
+        max_new_tokens=512,
+        do_sample=False,
+        eos_token_id=processor.tokenizer.eos_token_id,
+        pad_token_id=(
+            processor.tokenizer.pad_token_id
+            if processor.tokenizer.pad_token_id is not None
+            else processor.tokenizer.eos_token_id
+        ),
+    )
+    prediction = model.generate(
+        inputs, gen_config=gen_config, tokenizer=processor.tokenizer
+    )
+    print(f"prediction:", prediction)
diff --git a/tests/test_chatrex_region_caption.py b/tests/test_chatrex_region_caption.py
@@ -8,15 +8,15 @@
 if __name__ == "__main__":
     # load the processor
     processor = AutoProcessor.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         device_map="cuda",
     )
 
     print(f"loading chatrex model...")
     # load chatrex model
     model = AutoModelForCausalLM.from_pretrained(
-        "checkpoints/chatrex7b",
+        "IDEA-Research/ChatRex-7B",
         trust_remote_code=True,
         use_safetensors=True,
     ).to("cuda")