Spaces:
Sleeping
Sleeping
File size: 4,448 Bytes
202eff6 6ba63c9 8b45b0c 6ba63c9 8b45b0c 6ba63c9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 |
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import gradio as gr
import torch
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from huggingface_hub import hf_hub_download
from modeling.BaseModel import BaseModel
from modeling import build_model
from utilities.distributed import init_distributed
from utilities.arguments import load_opt_from_config_files
from utilities.constants import BIOMED_CLASSES
from inference_utils.inference import interactive_infer_image
def overlay_masks(image, masks, colors):
overlay = image.copy()
overlay = np.array(overlay, dtype=np.uint8)
for mask, color in zip(masks, colors):
overlay[mask > 0] = (overlay[mask > 0] * 0.4 + np.array(color) * 0.6).astype(
np.uint8
)
return Image.fromarray(overlay)
def generate_colors(n):
cmap = plt.get_cmap("tab10")
colors = [tuple(int(255 * val) for val in cmap(i)[:3]) for i in range(n)]
return colors
def init_model():
# Download model
model_file = hf_hub_download(
repo_id="microsoft/BiomedParse",
filename="biomedparse_v1.pt",
token=os.getenv("HF_TOKEN"),
)
# Initialize model
conf_files = "configs/biomedparse_inference.yaml"
opt = load_opt_from_config_files([conf_files])
opt = init_distributed(opt)
model = BaseModel(opt, build_model(opt)).from_pretrained(model_file).eval().cuda()
with torch.no_grad():
model.model.sem_seg_head.predictor.lang_encoder.get_text_embeddings(
BIOMED_CLASSES + ["background"], is_eval=True
)
return model
def predict(image, prompts):
if not prompts:
return None
# Convert string input to list
prompts = [p.strip() for p in prompts.split(",")]
# Convert to RGB if needed
if image.mode != "RGB":
image = image.convert("RGB")
# Get predictions
pred_mask = interactive_infer_image(model, image, prompts)
# Generate visualization
colors = generate_colors(len(prompts))
pred_overlay = overlay_masks(
image, [1 * (pred_mask[i] > 0.5) for i in range(len(prompts))], colors
)
return pred_overlay
def run():
global model
model = init_model()
demo = gr.Interface(
fn=predict,
inputs=[
gr.Image(type="pil", label="Input Image"),
gr.Textbox(
label="Prompts",
placeholder="Enter prompts separated by commas (e.g., neoplastic cells, inflammatory cells)",
),
],
outputs=gr.Image(type="pil", label="Prediction"),
title="BiomedParse Demo",
description="Upload a biomedical image and enter prompts (separated by commas) to detect specific features.",
examples=[
["examples/144DME_as_F.jpeg", "edema"],
["examples/C3_EndoCV2021_00462.jpg", "polyp"],
["examples/covid_1585.png", "left lung"],
["examples/covid_1585.png", "right lung"],
["examples/covid_1585.png", "COVID-19 infection"],
["examples/ISIC_0015551.jpg", "lesion"],
["examples/LIDC-IDRI-0140_143_280_CT_lung.png", "lung nodule"],
["examples/LIDC-IDRI-0140_143_280_CT_lung.png", "COVID-19 infection"],
[
"examples/Part_1_516_pathology_breast.png",
"connective tissue cells",
],
[
"examples/Part_1_516_pathology_breast.png",
"neoplastic cells",
],
[
"examples/Part_1_516_pathology_breast.png",
"neoplastic cells, inflammatory cells",
],
["examples/T0011.jpg", "optic disc"],
["examples/T0011.jpg", "optic cup"],
["examples/TCGA_HT_7856_19950831_8_MRI-FLAIR_brain.png", "glioma"],
],
)
demo.launch(server_name="0.0.0.0", server_port=7860)
if __name__ == "__main__":
run()
|