π Libra-Emo Model
A Multimodal Large Language Model for Fine-Grained Negative Emotion Detection
This is the official model release of Libra-Emo, a multimodal large language model for fine-grained negative emotion detection. The model is built upon InternVL 2.5 and fine-tuned on our Libra-Emo Dataset.
π Model Description
Libra-Emo Model is designed to understand and analyze emotions in video content. It can:
- Recognize 13 fine-grained emotion categories
- Provide detailed explanations for emotion classifications
- Process both visual and textual (subtitle) information
- Handle real-world video scenarios with complex emotional expressions
π Usage
Environment Setup
Our model is tested with CUDA 12.1. To set up the environment:
# Create and activate conda environment
conda create -n libra-emo python=3.10
conda activate libra-emo
# Clone and install InternVL dependencies
git clone https://github.com/OpenGVLab/InternVL.git
cd InternVL
pip install -r requirements/internvl_chat.txt
Usage Example
Here's a complete example of how to use Libra-Emo Model for video emotion analysis:
import numpy as np
import torch
import torchvision.transforms as T
from decord import VideoReader, cpu
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer
def build_transform(input_size):
MEAN = (0.485, 0.456, 0.406)
STD = (0.229, 0.224, 0.225)
transform = T.Compose(
[
T.Lambda(lambda img: img.convert("RGB") if img.mode != "RGB" else img),
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
T.ToTensor(),
T.Normalize(mean=MEAN, std=STD),
]
)
return transform
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
best_ratio_diff = float("inf")
best_ratio = (1, 1)
area = width * height
for ratio in target_ratios:
target_aspect_ratio = ratio[0] / ratio[1]
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
if ratio_diff < best_ratio_diff:
best_ratio_diff = ratio_diff
best_ratio = ratio
elif ratio_diff == best_ratio_diff:
if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
best_ratio = ratio
return best_ratio
def dynamic_preprocess(
image, min_num=1, max_num=12, image_size=448, use_thumbnail=False
):
orig_width, orig_height = image.size
aspect_ratio = orig_width / orig_height
# calculate the existing image aspect ratio
target_ratios = set(
(i, j)
for n in range(min_num, max_num + 1)
for i in range(1, n + 1)
for j in range(1, n + 1)
if i * j <= max_num and i * j >= min_num
)
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
# find the closest aspect ratio to the target
target_aspect_ratio = find_closest_aspect_ratio(
aspect_ratio, target_ratios, orig_width, orig_height, image_size
)
# calculate the target width and height
target_width = image_size * target_aspect_ratio[0]
target_height = image_size * target_aspect_ratio[1]
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
# resize the image
resized_img = image.resize((target_width, target_height))
processed_images = []
for i in range(blocks):
box = (
(i % (target_width // image_size)) * image_size,
(i // (target_width // image_size)) * image_size,
((i % (target_width // image_size)) + 1) * image_size,
((i // (target_width // image_size)) + 1) * image_size,
)
# split the image
split_img = resized_img.crop(box)
processed_images.append(split_img)
assert len(processed_images) == blocks
if use_thumbnail and len(processed_images) != 1:
thumbnail_img = image.resize((image_size, image_size))
processed_images.append(thumbnail_img)
return processed_images
def load_image(image_file, input_size=448, max_num=12):
image = Image.open(image_file).convert("RGB")
transform = build_transform(input_size=input_size)
images = dynamic_preprocess(
image, image_size=input_size, use_thumbnail=True, max_num=max_num
)
pixel_values = [transform(image) for image in images]
pixel_values = torch.stack(pixel_values)
return pixel_values
def get_index(bound, fps, max_frame, first_idx=0, num_segments=32):
if bound:
start, end = bound[0], bound[1]
else:
start, end = -100000, 100000
start_idx = max(first_idx, round(start * fps))
end_idx = min(round(end * fps), max_frame)
seg_size = float(end_idx - start_idx) / num_segments
frame_indices = np.array(
[
int(start_idx + (seg_size / 2) + np.round(seg_size * idx))
for idx in range(num_segments)
]
)
return frame_indices
def load_video(video_path, bound=None, input_size=448, max_num=1, num_segments=32):
vr = VideoReader(video_path, ctx=cpu(0), num_threads=1)
max_frame = len(vr) - 1
fps = float(vr.get_avg_fps())
pixel_values_list, num_patches_list = [], []
transform = build_transform(input_size=input_size)
frame_indices = get_index(
bound, fps, max_frame, first_idx=0, num_segments=num_segments
)
for frame_index in frame_indices:
img = Image.fromarray(vr[frame_index].asnumpy()).convert("RGB")
img = dynamic_preprocess(
img, image_size=input_size, use_thumbnail=True, max_num=max_num
)
pixel_values = [transform(tile) for tile in img]
pixel_values = torch.stack(pixel_values)
num_patches_list.append(pixel_values.shape[0])
pixel_values_list.append(pixel_values)
pixel_values = torch.cat(pixel_values_list)
return pixel_values, num_patches_list
# Step 1: load the model
# If you have an 80G A100 GPU, you can put the entire model on a single GPU.
model_path = "caskcsg/Libra-Emo-8B"
model = AutoModel.from_pretrained(
model_path,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True,
device_map="cuda:0"
)
model.eval()
tokenizer = AutoTokenizer.from_pretrained(
model_path, trust_remote_code=True, use_fast=False
)
# Step 2: load the video
video_path = "your_video_path" # change to your video path
pixel_values, num_patches_list = load_video(
video_path, num_segments=16, max_num=1
)
pixel_values = pixel_values.to(torch.bfloat16).to(model.device)
video_prefix = "".join(
[f"Frame-{i+1}: <image>\n" for i in range(len(num_patches_list))]
)
# Step 3: set the question
subtitle = None # change to your subtitle (subtitle is optional, if you don't have subtitle, please set it to None)
if subtitle is None:
question = (
video_prefix
+ "The above is a video. Please accurately identify the emotional label expressed by the people in the video. Emotional labels include should be limited to: happy, excited, angry, disgusted, hateful, surprised, amazed, frustrated, sad, fearful, despairful, ironic, neutral. The output format should be:\n[label]\n[explanation]"
)
else:
question = (
video_prefix
+ f"The above is a video. The video's subtitle is '{subtitle}', which maybe the words spoken by the person. Please accurately identify the emotional label expressed by the people in the video. Emotional labels include should be limited to: happy, excited, angry, disgusted, hateful, surprised, amazed, frustrated, sad, fearful, despairful, ironic, neutral. The output format should be:\n[label]\n[explanation]"
)
# Step 4: generate the response
response, history = model.chat(
tokenizer,
pixel_values,
question,
dict(max_new_tokens=512, do_sample=False),
num_patches_list=num_patches_list,
history=None,
return_history=True,
)
print(response)
The model will output the emotion label and explanation in the following format:
[label]
[explanation]
Note: If you aim to obtain emotion labels more quickly without requiring explanations, consider reducing the max_new_tokens
value in the generation configuration.
π Performance Comparison
We evaluate our models on the Libra-Emo Bench, comparing with both closed-source and open-source models. The evaluation metrics include accuracy and F1 scores for all emotions (13 classes) and negative emotions (8 classes).
Performance Comparison of MLLMs on Libra-Emo Bench
Model | Accuracy | Macro-F1 | Weighted-F1 | Accuracy (Neg) | Macro-F1 (Neg) | Weighted-F1 (Neg) |
---|---|---|---|---|---|---|
Closed-Source Models | ||||||
Gemini-2.0-Flash | 65.67 | 63.98 | 64.51 | 65.00 | 62.97 | 63.86 |
Gemini-1.5-Flash | 64.41 | 62.36 | 62.52 | 61.32 | 58.85 | 58.74 |
GPT-4o | 62.99 | 63.56 | 63.32 | 67.89 | 67.54 | 67.89 |
Claude-3.5-Sonnet | 52.13 | 48.38 | 49.38 | 49.47 | 49.32 | 50.50 |
Open-Source Models | ||||||
LLaVA-Video-7B-Qwen2 | 33.39 | 30.14 | 31.25 | 22.11 | 25.55 | 26.65 |
MiniCPM-o 2.6 (8B) | 42.83 | 40.23 | 40.26 | 40.53 | 37.29 | 38.00 |
Qwen2.5-VL-7B | 47.56 | 44.18 | 43.68 | 41.32 | 39.07 | 38.50 |
NVILA-8B | 41.89 | 35.92 | 36.01 | 42.89 | 32.83 | 33.88 |
Phi-3.5-vision-instruct | 53.39 | 51.23 | 51.16 | 52.89 | 49.97 | 49.98 |
InternVL-2.5-1B | 23.46 | 17.33 | 18.14 | 22.11 | 16.48 | 17.26 |
InternVL-2.5-2B | 25.98 | 22.31 | 22.19 | 30.79 | 24.97 | 24.59 |
InternVL-2.5-4B | 42.99 | 39.58 | 38.81 | 37.89 | 38.78 | 38.55 |
InternVL-2.5-8B | 54.96 | 51.42 | 51.64 | 50.53 | 47.07 | 47.22 |
Fine-Tuned on Libra-Emo | ||||||
Libra-Emo-1B | 53.54 (β30.08) | 49.44 (β32.11) | 50.19 (β32.05) | 46.84 (β24.73) | 41.53 (β25.05) | 42.25 (β24.99) |
Libra-Emo-2B | 56.38 (β30.40) | 53.60 (β31.29) | 53.90 (β31.71) | 50.26 (β19.47) | 48.79 (β23.82) | 48.91 (β24.32) |
Libra-Emo-4B | 65.20 (β22.21) | 64.12 (β24.54) | 64.41 (β25.60) | 60.79 (β22.90) | 61.30 (β22.52) | 61.61 (β23.06) |
Libra-Emo-8B | 71.18 (β16.22) | 70.51 (β19.09) | 70.71 (β19.07) | 70.53 (β20.00) | 69.94 (β22.87) | 70.14 (β22.92) |
Key Findings
- Our Libra-Emo models significantly outperform their base InternVL models, with improvements up to 30% in accuracy and F1 scores.
- The 8B version achieves the best performance, reaching 71.18% accuracy and 70.51% macro-F1 score on all emotions.
- For negative emotions, our models show strong performance with up to 70.53% accuracy and 70.14% weighted-F1 score.
- The performance scales well with model size, showing consistent improvements from 1B to 8B parameters.
Note: Our technical report with detailed methodology and analysis will be released soon.
- Downloads last month
- 1
Model tree for caskcsg/Libra-Emo-8B
Base model
OpenGVLab/InternVL2_5-8B