change bounding box label index to text

[hjsg1010]

❔Question

Hi, thanks for your great research and sharing codes.

I am applying YOLOv5 to my custom dataset.

And during learning, the mosaic section on wandb.ai shows the figure below.

However, I want to change the bbox label index to text label, such as '118' changes to 'cheesecake'.

What should I fix in code? or do I have to change my annotation?

Currently the data folder are consists of
data_folder/
┣ images/
┃ ┣ train/
┃ ┣ valid/
┣ labels/
┃ ┣ train/
┃ ┣ valid/
┣ data_config.yaml

Additional context

[github-actions]

👋 Hello @hjsg1010, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@hjsg1010 @kalenmike yes, your results are correct. The train mosaics only display the class index rather than the class name. You can see this in the Train Custom Data tutorial. We did this because the mosaics can get quite busy for high density datasets. The test dataset labels show the full name though, i.e. test_batch0_labels.jpg, so you may want to look at those instead.
https://docs.ultralytics.com/yolov5/tutorials/train_custom_data#local-logging

We're also developing dataset introspection tools as part of the new Ultralytics HUB. This should be ready sometime later on in summer 2021 at https://ultralytics.com

[hjsg1010]

@hjsg1010 @kalenmike yes, your results are correct. The train mosaics only display the class index rather than the class name. You can see this in the Train Custom Data tutorial. We did this because the mosaics can get quite busy for high density datasets. The test dataset labels show the full name though, i.e. test_batch0_labels.jpg, so you may want to look at those instead.
https://docs.ultralytics.com/yolov5/tutorials/train_custom_data#local-logging

We're also developing dataset introspection tools as part of the new Ultralytics HUB. This should be ready sometime later on in summer 2021 at https://ultralytics.com

oh, Thx for quick and kind reply.
Again, thx for sharing your codes!!

[hjsg1010]

@glenn-jocher
Hi, can I ask one more question?
I know that YOLO already does data augmentation.
However, I want to do custom data augmentation using Albumentations.
Then, where should I put augmentation pipeline code?
.utils/dataset.py ? or train.py?

sorry for my poor English skills, and low knowledge on object detection code..

[glenn-jocher]

@hjsg1010 you can inline any Albumentations augmentations you want in the dataloader here:

yolov5/utils/datasets.py

Lines 499 to 545 in 095197b

	def __getitem__(self, index):
	index = self.indices[index] # linear, shuffled, or image_weights
	hyp = self.hyp
	mosaic = self.mosaic and random.random() < hyp['mosaic']
	if mosaic:
	# Load mosaic
	img, labels = load_mosaic(self, index)
	shapes = None
	# MixUp https://arxiv.org/pdf/1710.09412.pdf
	if random.random() < hyp['mixup']:
	img2, labels2 = load_mosaic(self, random.randint(0, self.n - 1))
	r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
	img = (img * r + img2 * (1 - r)).astype(np.uint8)
	labels = np.concatenate((labels, labels2), 0)
	else:
	# Load image
	img, (h0, w0), (h, w) = load_image(self, index)
	# Letterbox
	shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
	img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
	shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
	labels = self.labels[index].copy()
	if labels.size: # normalized xywh to pixel xyxy format
	labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
	if self.augment:
	# Augment imagespace
	if not mosaic:
	img, labels = random_perspective(img, labels,
	degrees=hyp['degrees'],
	translate=hyp['translate'],
	scale=hyp['scale'],
	shear=hyp['shear'],
	perspective=hyp['perspective'])
	# Augment colorspace
	augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
	# Apply cutouts
	# if random.random() < 0.9:
	# labels = cutout(img, labels)

[hjsg1010]

@hjsg1010 you can inline any Albumentations augmentations you want in the dataloader here:

yolov5/utils/datasets.py

Lines 499 to 545 in 095197b

	def __getitem__(self, index):
	index = self.indices[index] # linear, shuffled, or image_weights
	hyp = self.hyp
	mosaic = self.mosaic and random.random() < hyp['mosaic']
	if mosaic:
	# Load mosaic
	img, labels = load_mosaic(self, index)
	shapes = None
	# MixUp https://arxiv.org/pdf/1710.09412.pdf
	if random.random() < hyp['mixup']:
	img2, labels2 = load_mosaic(self, random.randint(0, self.n - 1))
	r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
	img = (img * r + img2 * (1 - r)).astype(np.uint8)
	labels = np.concatenate((labels, labels2), 0)
	else:
	# Load image
	img, (h0, w0), (h, w) = load_image(self, index)
	# Letterbox
	shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
	img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
	shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
	labels = self.labels[index].copy()
	if labels.size: # normalized xywh to pixel xyxy format
	labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
	if self.augment:
	# Augment imagespace
	if not mosaic:
	img, labels = random_perspective(img, labels,
	degrees=hyp['degrees'],
	translate=hyp['translate'],
	scale=hyp['scale'],
	shear=hyp['shear'],
	perspective=hyp['perspective'])
	# Augment colorspace
	augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
	# Apply cutouts
	# if random.random() < 0.9:
	# labels = cutout(img, labels)

Thx for reply. Thankyou.

[glenn-jocher]

@hjsg1010 see PR #3882 for a proposed automatic Albumentations integration.