merge ultralytics:master

.github/workflows/greetings.yml

@@ -11,7 +11,7 @@ jobs:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           pr-message: |
             👋 Hello @${{ github.actor }}, thank you for submitting a 🚀 PR! To allow your work to be integrated as seamlessly as possible, we advise you to:
-            - ✅ Verify your PR is **up-to-date with origin/master.** If your PR is behind origin/master update by running the following, replacing 'feature' with the name of your local branch:
+            - ✅ Verify your PR is **up-to-date with origin/master.** If your PR is behind origin/master an automatic [GitHub actions](https://github.com/ultralytics/yolov5/blob/master/.github/workflows/rebase.yml) rebase may be attempted by including the /rebase command in a comment body, or by running the following code, replacing 'feature' with the name of your local branch:
             ```bash
             git remote add upstream https://github.com/ultralytics/yolov5.git
             git fetch upstream

Dockerfile

@@ -1,13 +1,13 @@
 # Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
-FROM nvcr.io/nvidia/pytorch:20.12-py3
+FROM nvcr.io/nvidia/pytorch:21.02-py3
 
 # Install linux packages
-RUN apt update && apt install -y screen libgl1-mesa-glx
+RUN apt update && apt install -y zip htop screen libgl1-mesa-glx
 
 # Install python dependencies
-RUN python -m pip install --upgrade pip
 COPY requirements.txt .
-RUN pip install -r requirements.txt gsutil
+RUN python -m pip install --upgrade pip
+RUN pip install --no-cache -r requirements.txt gsutil notebook
 
 # Create working directory
 RUN mkdir -p /usr/src/app
@@ -16,11 +16,8 @@ WORKDIR /usr/src/app
 # Copy contents
 COPY . /usr/src/app
 
-# Copy weights
-#RUN python3 -c "from models import *; \
-#attempt_download('weights/yolov5s.pt'); \
-#attempt_download('weights/yolov5m.pt'); \
-#attempt_download('weights/yolov5l.pt')"
+# Set environment variables
+ENV HOME=/usr/src/app
 
 
 # ---------------------------------------------------  Extras Below  ---------------------------------------------------

README.md

@@ -2,7 +2,7 @@
 <img src="https://user-images.githubusercontent.com/26833433/98699617-a1595a00-2377-11eb-8145-fc674eb9b1a7.jpg" width="1000"></a>
 &nbsp
 
-![CI CPU testing](https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg)
+<a href="https://github.com/ultralytics/yolov5/actions"><img src="https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg" alt="CI CPU testing"></a>
 
 This repository represents Ultralytics open-source research into future object detection methods, and incorporates lessons learned and best practices evolved over thousands of hours of training and evolution on anonymized client datasets. **All code and models are under active development, and are subject to modification or deletion without notice.** Use at your own risk.
 
@@ -50,6 +50,7 @@ $ pip install -r requirements.txt
 
 * [Train Custom Data](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data)&nbsp; 🚀 RECOMMENDED
 * [Weights & Biases Logging](https://github.com/ultralytics/yolov5/issues/1289)&nbsp; 🌟 NEW
+* [Supervisely Ecosystem](https://github.com/ultralytics/yolov5/issues/2518)&nbsp; 🌟 NEW
 * [Multi-GPU Training](https://github.com/ultralytics/yolov5/issues/475)
 * [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36)&nbsp; ⭐ NEW
 * [ONNX and TorchScript Export](https://github.com/ultralytics/yolov5/issues/251)
@@ -89,17 +90,15 @@ To run inference on example images in `data/images`:
 ```bash
 $ python detect.py --source data/images --weights yolov5s.pt --conf 0.25
 
-Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', img_size=640, iou_thres=0.45, save_conf=False, save_dir='runs/detect', save_txt=False, source='data/images/', update=False, view_img=False, weights=['yolov5s.pt'])
-Using torch 1.7.0+cu101 CUDA:0 (Tesla V100-SXM2-16GB, 16130MB)
-
-Downloading https://github.com/ultralytics/yolov5/releases/download/v3.1/yolov5s.pt to yolov5s.pt... 100%|██████████████| 14.5M/14.5M [00:00<00:00, 21.3MB/s]
+Namespace(agnostic_nms=False, augment=False, classes=None, conf_thres=0.25, device='', exist_ok=False, img_size=640, iou_thres=0.45, name='exp', project='runs/detect', save_conf=False, save_txt=False, source='data/images/', update=False, view_img=False, weights=['yolov5s.pt'])
+YOLOv5 v4.0-96-g83dc1b4 torch 1.7.0+cu101 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)
 
 Fusing layers... 
-Model Summary: 232 layers, 7459581 parameters, 0 gradients
-image 1/2 data/images/bus.jpg: 640x480 4 persons, 1 buss, 1 skateboards, Done. (0.012s)
-image 2/2 data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.012s)
-Results saved to runs/detect/exp
-Done. (0.113s)
+Model Summary: 224 layers, 7266973 parameters, 0 gradients, 17.0 GFLOPS
+image 1/2 /content/yolov5/data/images/bus.jpg: 640x480 4 persons, 1 bus, Done. (0.010s)
+image 2/2 /content/yolov5/data/images/zidane.jpg: 384x640 2 persons, 1 tie, Done. (0.011s)
+Results saved to runs/detect/exp2
+Done. (0.103s)
 ```
 <img src="https://user-images.githubusercontent.com/26833433/97107365-685a8d80-16c7-11eb-8c2e-83aac701d8b9.jpeg" width="500">  
 
@@ -108,18 +107,17 @@ Done. (0.113s)
 To run **batched inference** with YOLOv5 and [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36):
 ```python
 import torch
-from PIL import Image
 
 # Model
-model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True)
+model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
 
 # Images
-img1 = Image.open('zidane.jpg')
-img2 = Image.open('bus.jpg')
-imgs = [img1, img2]  # batched list of images
+dir = 'https://github.com/ultralytics/yolov5/raw/master/data/images/'
+imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')]  # batch of images
 
 # Inference
-result = model(imgs)
+results = model(imgs)
+results.print()  # or .show(), .save()
 ```
 
 

data/argoverse_hd.yaml

@@ -0,0 +1,21 @@
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_argoverse_hd.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../argoverse/Argoverse-1.1/images/train/  # 39384 images
+val: ../argoverse/Argoverse-1.1/images/val/  # 15062 iamges
+test: ../argoverse/Argoverse-1.1/images/test/  # Submit to: https://eval.ai/web/challenges/challenge-page/800/overview
+
+# number of classes
+nc: 8
+
+# class names
+names: [ 'person',  'bicycle',  'car',  'motorcycle',  'bus',  'truck',  'traffic_light',  'stop_sign' ]

data/scripts/get_argoverse_hd.sh

@@ -0,0 +1,62 @@
+#!/bin/bash
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Download command: bash data/scripts/get_argoverse_hd.sh
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+# Download/unzip images
+d='../argoverse/' # unzip directory
+mkdir $d
+url=https://argoverse-hd.s3.us-east-2.amazonaws.com/
+f=Argoverse-HD-Full.zip
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &# download, unzip, remove in background
+wait                                              # finish background tasks
+
+cd ../argoverse/Argoverse-1.1/
+ln -s tracking images
+
+cd ../Argoverse-HD/annotations/
+
+python3 - "$@" <<END
+import json
+from pathlib import Path
+
+annotation_files = ["train.json", "val.json"]
+print("Converting annotations to YOLOv5 format...")
+
+for val in annotation_files:
+    a = json.load(open(val, "rb"))
+
+    label_dict = {}
+    for annot in a['annotations']:
+        img_id = annot['image_id']
+        img_name = a['images'][img_id]['name']
+        img_label_name = img_name[:-3] + "txt"
+
+        obj_class = annot['category_id']
+        x_center, y_center, width, height = annot['bbox']
+        x_center = (x_center + width / 2) / 1920.  # offset and scale
+        y_center = (y_center + height / 2) / 1200.  # offset and scale
+        width /= 1920.  # scale
+        height /= 1200.  # scale
+
+        img_dir = "./labels/" + a['seq_dirs'][a['images'][annot['image_id']]['sid']]
+
+        Path(img_dir).mkdir(parents=True, exist_ok=True)
+
+        if img_dir + "/" + img_label_name not in label_dict:
+            label_dict[img_dir + "/" + img_label_name] = []
+
+        label_dict[img_dir + "/" + img_label_name].append(f"{obj_class} {x_center} {y_center} {width} {height}\n")
+
+    for filename in label_dict:
+        with open(filename, "w") as file:
+            for string in label_dict[filename]:
+                file.write(string)
+
+END
+
+mv ./labels ../../Argoverse-1.1/

data/scripts/get_coco.sh

@@ -10,8 +10,9 @@
 # Download/unzip labels
 d='../' # unzip directory
 url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
-f='coco2017labels.zip'                                                                 # 68 MB
-echo 'Downloading' $url$f ' ...' && curl -L $url$f -o $f && unzip -q $f -d $d && rm $f # download, unzip, remove
+f='coco2017labels.zip' # or 'coco2017labels-segments.zip', 68 MB
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
 
 # Download/unzip images
 d='../coco/images' # unzip directory
@@ -20,7 +21,7 @@ f1='train2017.zip' # 19G, 118k images
 f2='val2017.zip'   # 1G, 5k images
 f3='test2017.zip'  # 7G, 41k images (optional)
 for f in $f1 $f2; do
-  echo 'Downloading' $url$f '...' && curl -L $url$f -o $f # download, (unzip, remove in background)
-  unzip -q $f -d $d && rm $f &
+  echo 'Downloading' $url$f '...'
+  curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
 done
 wait # finish background tasks

data/scripts/get_voc.sh

@@ -18,8 +18,8 @@ f1=VOCtrainval_06-Nov-2007.zip # 446MB, 5012 images
 f2=VOCtest_06-Nov-2007.zip     # 438MB, 4953 images
 f3=VOCtrainval_11-May-2012.zip # 1.95GB, 17126 images
 for f in $f3 $f2 $f1; do
-  echo 'Downloading' $url$f '...' && curl -L $url$f -o $f # download, (unzip, remove in background)
-  unzip -q $f -d $d && rm $f &
+  echo 'Downloading' $url$f '...' 
+  curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
 done
 wait # finish background tasks
 

detect.py

@@ -11,14 +11,15 @@
 
 from models.experimental import attempt_load
 from utils.datasets import LoadStreams, LoadImages
-from utils.general import check_img_size, check_requirements, non_max_suppression, apply_classifier, scale_coords, \
-    xyxy2xywh, strip_optimizer, set_logging, increment_path
+from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
+    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
 from utils.plots import plot_one_box
 from utils.torch_utils import select_device, load_classifier, time_synchronized
 
 
 def detect(save_img=False):
     source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
+    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
     webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
         ('rtsp://', 'rtmp://', 'http://'))
 
@@ -46,6 +47,7 @@ def detect(save_img=False):
         import tensorflow as tf
         from tensorflow import keras
 
+        stride = None
         with open('data/coco.yaml') as f:
             names = yaml.load(f, Loader=yaml.FullLoader)['names']  # class names (assume COCO)
 
@@ -92,12 +94,11 @@ def _imports_graph_def():
     # Set Dataloader
     vid_path, vid_writer = None, None
     if webcam:
-        view_img = True
+        view_img = check_imshow()
         cudnn.benchmark = True  # set True to speed up constant image size inference
-        dataset = LoadStreams(source, img_size=imgsz, stride=stride if backend == 'pytorch' else None, auto=backend == 'pytorch')
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=backend == 'pytorch')
     else:
-        save_img = True
-        dataset = LoadImages(source, img_size=imgsz, stride=stride if backend == 'pytorch' else None, auto=backend == 'pytorch')
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=backend == 'pytorch')
 
     # Get names and colors
     colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
@@ -189,22 +190,25 @@ def _imports_graph_def():
             # Stream results
             if view_img:
                 cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
 
             # Save results (image with detections)
             if save_img:
                 if dataset.mode == 'image':
                     cv2.imwrite(save_path, im0)
-                else:  # 'video'
+                else:  # 'video' or 'stream'
                     if vid_path != save_path:  # new video
                         vid_path = save_path
                         if isinstance(vid_writer, cv2.VideoWriter):
                             vid_writer.release()  # release previous video writer
-
-                        fourcc = 'mp4v'  # output video codec
-                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
-                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                            save_path += '.mp4'
+                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                     vid_writer.write(im0)
 
     if save_txt or save_img:
@@ -225,6 +229,7 @@ def _imports_graph_def():
     parser.add_argument('--view-img', action='store_true', help='display results')
     parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
     parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
     parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
     parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
     parser.add_argument('--augment', action='store_true', help='augmented inference')
@@ -236,7 +241,7 @@ def _imports_graph_def():
     opt = parser.parse_args()
     opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
     print(opt)
-    check_requirements()
+    check_requirements(exclude=('pycocotools', 'thop'))
 
     with torch.no_grad():
         if opt.update:  # update all models (to fix SourceChangeWarning)