Merge pull request CASIA-IVA-Lab#231 from CASIA-IVA-Lab/dev

Optimized the jagged edges issue in segmentation.

Author: zxDeepDiver

README.md

@@ -44,7 +44,7 @@ cd FastSAM
 pip install -r requirements.txt
 ```
 
-Install CLIP:
+Install CLIP(Required if the text prompt is being tested.):
 
 ```shell
 pip install git+https://github.com/openai/CLIP.git

fastsam/decoder.py

@@ -1,7 +1,6 @@
 from .model import FastSAM
 import numpy as np
 from PIL import Image
-import clip
 from typing import Optional, List, Tuple, Union
 
 

fastsam/prompt.py

@@ -7,15 +7,6 @@
 from .utils import image_to_np_ndarray
 from PIL import Image
 
-try:
-    import clip  # for linear_assignment
-
-except (ImportError, AssertionError, AttributeError):
-    from ultralytics.yolo.utils.checks import check_requirements
-
-    check_requirements('git+https://github.com/openai/CLIP.git')  # required before installing lap from source
-    import clip
-
 
 class FastSAMPrompt:
 
@@ -340,6 +331,16 @@ def fast_show_mask_gpu(
     @torch.no_grad()
     def retrieve(self, model, preprocess, elements, search_text: str, device) -> int:
         preprocessed_images = [preprocess(image).to(device) for image in elements]
+        try:
+           import clip  # for linear_assignment
+    
+        except (ImportError, AssertionError, AttributeError):
+           from ultralytics.yolo.utils.checks import check_requirements
+    
+           check_requirements('git+https://github.com/openai/CLIP.git')  # required before installing lap from source
+           import clip
+
+
         tokenized_text = clip.tokenize([search_text]).to(device)
         stacked_images = torch.stack(preprocessed_images)
         image_features = model.encode_image(stacked_images)

requirements.txt

@@ -15,5 +15,5 @@ seaborn>=0.11.0
 gradio==3.35.2
 
 # Ultralytics-----------------------------------
-ultralytics == 8.0.120
+# ultralytics == 8.0.120
 

ultralytics/.pre-commit-config.yaml

@@ -0,0 +1,73 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Pre-commit hooks. For more information see https://github.com/pre-commit/pre-commit-hooks/blob/main/README.md
+
+exclude: 'docs/'
+# Define bot property if installed via https://github.com/marketplace/pre-commit-ci
+ci:
+  autofix_prs: true
+  autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions'
+  autoupdate_schedule: monthly
+  # submodules: true
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.4.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: check-case-conflict
+      # - id: check-yaml
+      - id: check-docstring-first
+      - id: double-quote-string-fixer
+      - id: detect-private-key
+
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.4.0
+    hooks:
+      - id: pyupgrade
+        name: Upgrade code
+
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort
+        name: Sort imports
+
+  - repo: https://github.com/google/yapf
+    rev: v0.33.0
+    hooks:
+      - id: yapf
+        name: YAPF formatting
+
+  - repo: https://github.com/executablebooks/mdformat
+    rev: 0.7.16
+    hooks:
+      - id: mdformat
+        name: MD formatting
+        additional_dependencies:
+          - mdformat-gfm
+          - mdformat-black
+        # exclude: "README.md|README.zh-CN.md|CONTRIBUTING.md"
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 6.0.0
+    hooks:
+      - id: flake8
+        name: PEP8
+
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.2.4
+    hooks:
+      - id: codespell
+        args:
+          - --ignore-words-list=crate,nd,strack,dota
+
+#  - repo: https://github.com/asottile/yesqa
+#    rev: v1.4.0
+#    hooks:
+#      - id: yesqa
+
+#  - repo: https://github.com/asottile/dead
+#    rev: v1.5.0
+#    hooks:
+#    -   id: dead

ultralytics/__init__.py

@@ -0,0 +1,12 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+__version__ = '8.0.120'
+
+from ultralytics.hub import start
+from ultralytics.vit.rtdetr import RTDETR
+from ultralytics.vit.sam import SAM
+from ultralytics.yolo.engine.model import YOLO
+from ultralytics.yolo.nas import NAS
+from ultralytics.yolo.utils.checks import check_yolo as checks
+
+__all__ = '__version__', 'YOLO', 'NAS', 'SAM', 'RTDETR', 'checks', 'start'  # allow simpler import

ultralytics/assets/bus.jpg

@@ -0,0 +1,73 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI
+# Example usage: yolo train data=Argoverse.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── Argoverse  ← downloads here (31.3 GB)
+
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/Argoverse  # dataset root dir
+train: Argoverse-1.1/images/train/  # train images (relative to 'path') 39384 images
+val: Argoverse-1.1/images/val/  # val images (relative to 'path') 15062 images
+test: Argoverse-1.1/images/test/  # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: bus
+  5: truck
+  6: traffic_light
+  7: stop_sign
+
+
+# Download script/URL (optional) ---------------------------------------------------------------------------------------
+download: |
+  import json
+  from tqdm import tqdm
+  from ultralytics.yolo.utils.downloads import download
+  from pathlib import Path
+
+  def argoverse2yolo(set):
+      labels = {}
+      a = json.load(open(set, "rb"))
+      for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."):
+          img_id = annot['image_id']
+          img_name = a['images'][img_id]['name']
+          img_label_name = f'{img_name[:-3]}txt'
+
+          cls = annot['category_id']  # instance class id
+          x_center, y_center, width, height = annot['bbox']
+          x_center = (x_center + width / 2) / 1920.0  # offset and scale
+          y_center = (y_center + height / 2) / 1200.0  # offset and scale
+          width /= 1920.0  # scale
+          height /= 1200.0  # scale
+
+          img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']]
+          if not img_dir.exists():
+              img_dir.mkdir(parents=True, exist_ok=True)
+
+          k = str(img_dir / img_label_name)
+          if k not in labels:
+              labels[k] = []
+          labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n")
+
+      for k in labels:
+          with open(k, "w") as f:
+              f.writelines(labels[k])
+
+
+  # Download
+  dir = Path(yaml['path'])  # dataset root dir
+  urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip']
+  download(urls, dir=dir)
+
+  # Convert
+  annotations_dir = 'Argoverse-HD/annotations/'
+  (dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images')  # rename 'tracking' to 'images'
+  for d in "train.json", "val.json":
+      argoverse2yolo(dir / annotations_dir / d)  # convert VisDrone annotations to YOLO labels

ultralytics/assets/zidane.jpg

@@ -0,0 +1,54 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# Global Wheat 2020 dataset http://www.global-wheat.com/ by University of Saskatchewan
+# Example usage: yolo train data=GlobalWheat2020.yaml
+# parent
+# ├── ultralytics
+# └── datasets
+#     └── GlobalWheat2020  ← downloads here (7.0 GB)
+
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/GlobalWheat2020  # dataset root dir
+train: # train images (relative to 'path') 3422 images
+  - images/arvalis_1
+  - images/arvalis_2
+  - images/arvalis_3
+  - images/ethz_1
+  - images/rres_1
+  - images/inrae_1
+  - images/usask_1
+val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1)
+  - images/ethz_1
+test: # test images (optional) 1276 images
+  - images/utokyo_1
+  - images/utokyo_2
+  - images/nau_1
+  - images/uq_1
+
+# Classes
+names:
+  0: wheat_head
+
+
+# Download script/URL (optional) ---------------------------------------------------------------------------------------
+download: |
+  from ultralytics.yolo.utils.downloads import download
+  from pathlib import Path
+
+  # Download
+  dir = Path(yaml['path'])  # dataset root dir
+  urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+          'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+  download(urls, dir=dir)
+
+  # Make Directories
+  for p in 'annotations', 'images', 'labels':
+      (dir / p).mkdir(parents=True, exist_ok=True)
+
+  # Move
+  for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+           'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+      (dir / 'global-wheat-codalab-official' / p).rename(dir / 'images' / p)  # move to /images
+      f = (dir / 'global-wheat-codalab-official' / p).with_suffix('.json')  # json file
+      if f.exists():
+          f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations