How to get simple inference result as txt

[halzhen]

Search before asking

• I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

I am trying to inference on a batch of images in a directory. The basic inference code is the one used , I have already read the documentation for the Detections return, is there any way to get the detected objects as .txt ? In a similar way to result.print() , it shows the objects and the times they appear.

I am aware that detect.py can save as .txt but couldn't do inference on batch of images with it.

model = torch.hub.load('ultralytics/yolov5', 'yolov5s')

# Images
directory = 'keyframes/'

frames = [] # batch of images
for filename in os.listdir(directory):
    frame = Image.open('keyframes/'+filename)
    frames.append(frame)

# Inference
results = model(frames, size=640) 

# Results
results.print()
results.save()  ```

What I need is the objects detected in a .txt file without using detect.py, but if detect.py can be modified to work on batch of images from a directory that would also work. 


### Additional

_No response_

[github-actions]

👋 Hello @kzhenzhou, 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.

Requirements

Python>=3.6.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

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), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[glenn-jocher]

@kzhenzhou that's funny, you are right there is no --save-txt method for PyTorch Hub models. You could submit a PR to add such a method, i.e.:

results.save_txt()

yolov5/models/common.py

Lines 551 to 650 in bd815d4

	class Detections:
	# YOLOv5 detections class for inference results
	def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None):
	super().__init__()
	d = pred[0].device # device
	gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations
	self.imgs = imgs # list of images as numpy arrays
	self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
	self.names = names # class names
	self.files = files # image filenames
	self.times = times # profiling times
	self.xyxy = pred # xyxy pixels
	self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
	self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
	self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
	self.n = len(self.pred) # number of images (batch size)
	self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
	self.s = shape # inference BCHW shape
	def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
	crops = []
	for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
	s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
	if pred.shape[0]:
	for c in pred[:, -1].unique():
	n = (pred[:, -1] == c).sum() # detections per class
	s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
	if show or save or render or crop:
	annotator = Annotator(im, example=str(self.names))
	for *box, conf, cls in reversed(pred): # xyxy, confidence, class
	label = f'{self.names[int(cls)]} {conf:.2f}'
	if crop:
	file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
	crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
	'im': save_one_box(box, im, file=file, save=save)})
	else: # all others
	annotator.box_label(box, label, color=colors(cls))
	im = annotator.im
	else:
	s += '(no detections)'
	im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
	if pprint:
	LOGGER.info(s.rstrip(', '))
	if show:
	im.show(self.files[i]) # show
	if save:
	f = self.files[i]
	im.save(save_dir / f) # save
	if i == self.n - 1:
	LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
	if render:
	self.imgs[i] = np.asarray(im)
	if crop:
	if save:
	LOGGER.info(f'Saved results to {save_dir}\n')
	return crops
	def print(self):
	self.display(pprint=True) # print results
	LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
	self.t)
	def show(self):
	self.display(show=True) # show results
	def save(self, save_dir='runs/detect/exp'):
	save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
	self.display(save=True, save_dir=save_dir) # save results
	def crop(self, save=True, save_dir='runs/detect/exp'):
	save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
	return self.display(crop=True, save=save, save_dir=save_dir) # crop results
	def render(self):
	self.display(render=True) # render results
	return self.imgs
	def pandas(self):
	# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
	new = copy(self) # return copy
	ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
	cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
	for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
	a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
	setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
	return new
	def tolist(self):
	# return a list of Detections objects, i.e. 'for result in results.tolist():'
	r = range(self.n) # iterable
	x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
	# for d in x:
	# for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
	# setattr(d, k, getattr(d, k)[0]) # pop out of list
	return x
	def __len__(self):
	return self.n

I'll add a TODO here since this seems like a useful feature to have, but we are quite busy so I can not provide an estimated implementation timeline if we do this ourselves.

TODO: results.save_txt() method.

[SarperYurttas]

@glenn-jocher I want to work on this if it's ok?

[glenn-jocher]

@SarperYurttas awesome, yes go for it!

[Symbadian]

@kzhenzhou that's funny, you are right there is no --save-txt method for PyTorch Hub models. You could submit a PR to add such a method, i.e.:

results.save_txt()

yolov5/models/common.py

Lines 551 to 650 in bd815d4

	class Detections:
	# YOLOv5 detections class for inference results
	def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None):
	super().__init__()
	d = pred[0].device # device
	gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations
	self.imgs = imgs # list of images as numpy arrays
	self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
	self.names = names # class names
	self.files = files # image filenames
	self.times = times # profiling times
	self.xyxy = pred # xyxy pixels
	self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
	self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
	self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
	self.n = len(self.pred) # number of images (batch size)
	self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
	self.s = shape # inference BCHW shape
	def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
	crops = []
	for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
	s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
	if pred.shape[0]:
	for c in pred[:, -1].unique():
	n = (pred[:, -1] == c).sum() # detections per class
	s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
	if show or save or render or crop:
	annotator = Annotator(im, example=str(self.names))
	for *box, conf, cls in reversed(pred): # xyxy, confidence, class
	label = f'{self.names[int(cls)]} {conf:.2f}'
	if crop:
	file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
	crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
	'im': save_one_box(box, im, file=file, save=save)})
	else: # all others
	annotator.box_label(box, label, color=colors(cls))
	im = annotator.im
	else:
	s += '(no detections)'
	im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
	if pprint:
	LOGGER.info(s.rstrip(', '))
	if show:
	im.show(self.files[i]) # show
	if save:
	f = self.files[i]
	im.save(save_dir / f) # save
	if i == self.n - 1:
	LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
	if render:
	self.imgs[i] = np.asarray(im)
	if crop:
	if save:
	LOGGER.info(f'Saved results to {save_dir}\n')
	return crops
	def print(self):
	self.display(pprint=True) # print results
	LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
	self.t)
	def show(self):
	self.display(show=True) # show results
	def save(self, save_dir='runs/detect/exp'):
	save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
	self.display(save=True, save_dir=save_dir) # save results
	def crop(self, save=True, save_dir='runs/detect/exp'):
	save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
	return self.display(crop=True, save=save, save_dir=save_dir) # crop results
	def render(self):
	self.display(render=True) # render results
	return self.imgs
	def pandas(self):
	# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
	new = copy(self) # return copy
	ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
	cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
	for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
	a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
	setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
	return new
	def tolist(self):
	# return a list of Detections objects, i.e. 'for result in results.tolist():'
	r = range(self.n) # iterable
	x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
	# for d in x:
	# for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
	# setattr(d, k, getattr(d, k)[0]) # pop out of list
	return x
	def __len__(self):
	return self.n

I'll add a TODO here since this seems like a useful feature to have, but we are quite busy so I can not provide an estimated implementation timeline if we do this ourselves.

TODO: results.save_txt() method.

Hi @glenn-jocher,

is there anyway to get the heading of the result type saved as well in the output files?

for example:

epoch | loss | acc | val_loss | val_acc
| | | |

Currently, in the save files the data is presented as the example below without headings in .txt format
0 1.64137483 0.27450982 0.8043378 0.46153846

I tried --save-txt with save --save-conf but none is presenting the headings for the processing results...

I am trying to do a basic decision process but these bits are not available!

Thanx for responding and acknowledging my digital presence, really appreciate this!

[glenn-jocher]

@Symbadian Thanks for reaching out! We appreciate your support and contribution to the YOLOv5 community. Currently, the --save-txt option does not include column headings in the saved .txt file. However, you can easily manipulate the .txt file after saving it to include headings using any text manipulation tool or a simple script. We appreciate your understanding and contributions. Good luck with your work!