How to visualize feature mapping on YOLOV5s?

[Mashood3624]

❔Question

I have been searching for hours but I cannot find a single repo or issue on github which tells how can we visualize feature maps of a yolo model.

Sample:

Additional context

[github-actions]

👋 Hello @Mashood3624, 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]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

[thanhphuchuynh]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

I tried it and it worked! thanks 👍

for ii in range(len(x[i][0].permute(3, 0, 1, 2))):
    plt.subplot(3,7,ii+1)
    b =  np.array(255*x[i][0].permute(3, 0, 1, 2)[ii, :, :, :].permute(1, 2, 0).cpu().detach().numpy()[:, :, ::-1])
    plt.imshow(cv2.cvtColor(b.astype('uint8'), cv2.COLOR_BGR2RGB))
    plt.axis("off")
plt.show()

[glenn-jocher]

Oh great! Though I think there may be a bug in your plotting code, as the feature maps lack any concept of RGB or BGR 'colors'. You may have confused the anchor dimension for a color dimension.

[thanhphuchuynh]

After i remove RGB and BGR in my code.
the result:

[glenn-jocher]

@thanhphuchuynh the feature maps have no concept of RGB or BGR as I said, but your images are in color. The channel dimension that inputs 3 colors is stretched to over a thousand channels eventually, but none of them are paired in 3s for color.

[thanhphuchuynh]

i tried again and result. thanks sir <3

[glenn-jocher]

@thanhphuchuynh interesting!

[wanghangege]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

I tried it and it worked! thanks 👍

for ii in range(len(x[i][0].permute(3, 0, 1, 2))):
    plt.subplot(3,7,ii+1)
    b =  np.array(255*x[i][0].permute(3, 0, 1, 2)[ii, :, :, :].permute(1, 2, 0).cpu().detach().numpy()[:, :, ::-1])
    plt.imshow(cv2.cvtColor(b.astype('uint8'), cv2.COLOR_BGR2RGB))
    plt.axis("off")
plt.show()

Hello, I'm a novice. I'd like to ask you, where should the visual code you disclose be inserted?

[thanhphuchuynh]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

I tried it and it worked! thanks 👍

for ii in range(len(x[i][0].permute(3, 0, 1, 2))):
    plt.subplot(3,7,ii+1)
    b =  np.array(255*x[i][0].permute(3, 0, 1, 2)[ii, :, :, :].permute(1, 2, 0).cpu().detach().numpy()[:, :, ::-1])
    plt.imshow(cv2.cvtColor(b.astype('uint8'), cv2.COLOR_BGR2RGB))
    plt.axis("off")
plt.show()

Hello, I'm a novice. I'd like to ask you, where should the visual code you disclose be inserted?

In the model forward method, you should custom again code.

[GiorgioSgl]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

I tried it and it worked! thanks +1

for ii in range(len(x[i][0].permute(3, 0, 1, 2))):
    plt.subplot(3,7,ii+1)
    b =  np.array(255*x[i][0].permute(3, 0, 1, 2)[ii, :, :, :].permute(1, 2, 0).cpu().detach().numpy()[:, :, ::-1])
    plt.imshow(cv2.cvtColor(b.astype('uint8'), cv2.COLOR_BGR2RGB))
    plt.axis("off")
plt.show()

Hello, I'm a novice. I'd like to ask you, where should the visual code you disclose be inserted?

Have you understand how to plot the feature maps?

[wanghangege]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

I tried it and it worked! thanks +1

for ii in range(len(x[i][0].permute(3, 0, 1, 2))):
    plt.subplot(3,7,ii+1)
    b =  np.array(255*x[i][0].permute(3, 0, 1, 2)[ii, :, :, :].permute(1, 2, 0).cpu().detach().numpy()[:, :, ::-1])
    plt.imshow(cv2.cvtColor(b.astype('uint8'), cv2.COLOR_BGR2RGB))
    plt.axis("off")
plt.show()

Hello, I'm a novice. I'd like to ask you, where should the visual code you disclose be inserted?

Have you understand how to plot the feature maps?

yes, I know. 应该是在前向传播中添加可视化程序即可。

[Mashood3624]

Hi, I have tried implementing feature maps from @thanhphuchuynh repo but It dont look great. @glenn-jocher Can you confirm if it is right or not ?

https://github.com/ThanhPhucHuynh/yolov5_xray/blob/a52b9934b2912840c7df6a4e60c5910aeda96e68/models/yolo.py

here is some pictures

[glenn-jocher]

@Mashood3624 thats incorrect.

Feature maps are square for 640x640 inputs and there are more than a thousand of them in a YOLOv5l output.

[glenn-jocher]

@Mashood3624 good news 😃! Feature map visualization was added ✅ in PR #3804 by @Zigars today. This allows for visualizing feature maps from any part of the model from any function (i.e. detect.py, train.py, test.py). Feature maps are saved as *.png files in runs/features/exp directory. To turn on feature visualization set feature_vis=True in the model forward method and define the layer you want to visualize (default is SPP layer).

yolov5/models/yolo.py

Lines 158 to 160 in 20d45aa

	if feature_vis and m.type == 'models.common.SPP':
	feature_visualization(x, m.type, m.i)

To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload with model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

[Mashood3624]

Thank you @glenn-jocher 😊

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!

[ControllableGeneration]

1, I realize that below if not os.path.isdir(save_dir): os.mkdir(save_dir) need to be added to the 432nd line of utils/plots.py in order to not get a file or directory not found error
2, and you should do plt.close() after plt.savefig() in order to avoid opening too many images

[glenn-jocher]

@ZiyuBao making directories is handled in detect.py here:

yolov5/detect.py

Lines 113 to 114 in 2d99063

	visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
	pred = model(img, augment=augment, visualize=visualize)[0]

matplotlib is actually placed in a mode where it doesn't produce any windows here, so I think we can skip plt.close() calls

yolov5/utils/plots.py

Lines 20 to 22 in 2d99063

	# Settings
	matplotlib.rc('font', **{'size': 11})
	matplotlib.use('Agg') # for writing to files only

[noreenanwar]

Hi, how can we visualize class probability map after detection?

[glenn-jocher]

👋 Hello! Thanks for asking about feature visualization. YOLOv5 🚀 features can be visualized through all stages of the model from input to output. To visualize features from a given source run detect.py with the --visualize flag:

python detect.py --weights yolov5s.pt --source data/images/bus.jpg --visualize

An example Notebook visualizing bus.jpg features with YOLOv5s is shown below:

All stages are visualized by default, each with its own PNG showing the first 32 feature maps output from that stage. You can open any PNG for a closer look. For example the first 32 feature maps of the Focus() layer output are shown in stage0_Focus_features.png:

Feature maps may be customized by updating the feature_visualization() function in utils/plots.py:

yolov5/utils/plots.py

Lines 403 to 427 in bb5ebc2

	def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
	"""
	x: Features to be visualized
	module_type: Module type
	stage: Module stage within model
	n: Maximum number of feature maps to plot
	save_dir: Directory to save results
	"""
	if 'Detect' not in module_type:
	batch, channels, height, width = x.shape # batch, channels, height, width
	if height > 1 and width > 1:
	f = f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
	blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
	n = min(n, channels) # number of plots
	fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
	ax = ax.ravel()
	plt.subplots_adjust(wspace=0.05, hspace=0.05)
	for i in range(n):
	ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
	ax[i].axis('off')
	print(f'Saving {save_dir / f}... ({n}/{channels})')
	plt.savefig(save_dir / f, dpi=300, bbox_inches='tight')
	plt.close()

Good luck 🍀 and let us know if you have any other questions!

[noreenanwar]

Hi, Thanks for your reply.
I want to visualize only detected objects.It is possible to only get the class probability maps ?

[glenn-jocher]

@noreenanwar class probability vectors are stripped in the NMS function, you can access the full vectors there:

yolov5/utils/general.py

Lines 776 to 875 in 0c13240

	def non_max_suppression(prediction,
	conf_thres=0.25,
	iou_thres=0.45,
	classes=None,
	agnostic=False,
	multi_label=False,
	labels=(),
	max_det=300):
	"""Non-Maximum Suppression (NMS) on inference results to reject overlapping bounding boxes
	Returns:
	list of detections, on (n,6) tensor per image [xyxy, conf, cls]
	"""
	bs = prediction.shape[0] # batch size
	nc = prediction.shape[2] - 5 # number of classes
	xc = prediction[..., 4] > conf_thres # candidates
	# Checks
	assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
	assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
	# Settings
	# min_wh = 2 # (pixels) minimum box width and height
	max_wh = 7680 # (pixels) maximum box width and height
	max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
	time_limit = 0.3 + 0.03 * bs # seconds to quit after
	redundant = True # require redundant detections
	multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
	merge = False # use merge-NMS
	t = time.time()
	output = [torch.zeros((0, 6), device=prediction.device)] * bs
	for xi, x in enumerate(prediction): # image index, image inference
	# Apply constraints
	# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
	x = x[xc[xi]] # confidence
	# Cat apriori labels if autolabelling
	if labels and len(labels[xi]):
	lb = labels[xi]
	v = torch.zeros((len(lb), nc + 5), device=x.device)
	v[:, :4] = lb[:, 1:5] # box
	v[:, 4] = 1.0 # conf
	v[range(len(lb)), lb[:, 0].long() + 5] = 1.0 # cls
	x = torch.cat((x, v), 0)
	# If none remain process next image
	if not x.shape[0]:
	continue
	# Compute conf
	x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
	# Box (center x, center y, width, height) to (x1, y1, x2, y2)
	box = xywh2xyxy(x[:, :4])
	# Detections matrix nx6 (xyxy, conf, cls)
	if multi_label:
	i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
	x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
	else: # best class only
	conf, j = x[:, 5:].max(1, keepdim=True)
	x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
	# Filter by class
	if classes is not None:
	x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
	# Apply finite constraint
	# if not torch.isfinite(x).all():
	# x = x[torch.isfinite(x).all(1)]
	# Check shape
	n = x.shape[0] # number of boxes
	if not n: # no boxes
	continue
	elif n > max_nms: # excess boxes
	x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
	# Batched NMS
	c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
	boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
	i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
	if i.shape[0] > max_det: # limit detections
	i = i[:max_det]
	if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
	# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
	iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
	weights = iou * scores[None] # box weights
	x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
	if redundant:
	i = i[iou.sum(1) > 1] # require redundancy
	output[xi] = x[i]
	if (time.time() - t) > time_limit:
	LOGGER.warning(f'WARNING: NMS time limit {time_limit:.3f}s exceeded')
	break # time limit exceeded
	return output

[noreenanwar]

I should add the following lines in this file?.

visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
pred = model(img, augment=augment, visualize=visualize)[0]

[glenn-jocher]

@noreenanwar yes, you can customize the visualization output by adding those lines to the file. Make sure to also define the save_dir variable, which should hold the path where you want to save the visualizations. This will allow you to generate and save only the desired class probability maps. Let me know if you need further help with this!

[Muhammad-237]

@Mashood3624 you should be able to visualize data anywhere in the model by inserting your own plotting routines wherever you want. The model forward method is probably a good place to start:

yolov5/models/yolo.py

Lines 72 to 118 in 525f4f8

	class Model(nn.Module):
	def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
	super(Model, self).__init__()
	if isinstance(cfg, dict):
	self.yaml = cfg # model dict
	else: # is *.yaml
	import yaml # for torch hub
	self.yaml_file = Path(cfg).name
	with open(cfg) as f:
	self.yaml = yaml.safe_load(f) # model dict
	# Define model
	ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
	if nc and nc != self.yaml['nc']:
	logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
	self.yaml['nc'] = nc # override yaml value
	if anchors:
	logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
	self.yaml['anchors'] = round(anchors) # override yaml value
	self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
	self.names = [str(i) for i in range(self.yaml['nc'])] # default names
	self.inplace = self.yaml.get('inplace', True)
	# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
	# Build strides, anchors
	m = self.model[-1] # Detect()
	if isinstance(m, Detect):
	s = 256 # 2x min stride
	m.inplace = self.inplace
	m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
	m.anchors /= m.stride.view(-1, 1, 1)
	check_anchor_order(m)
	self.stride = m.stride
	self._initialize_biases() # only run once
	# logger.info('Strides: %s' % m.stride.tolist())
	# Init weights, biases
	initialize_weights(self)
	self.info()
	logger.info('')
	def forward(self, x, augment=False, profile=False):
	if augment:
	return self.forward_augment(x) # augmented inference, None
	else:
	return self.forward_once(x, profile) # single-scale inference, train

I tried it and it worked! thanks 👍

for ii in range(len(x[i][0].permute(3, 0, 1, 2))):
    plt.subplot(3,7,ii+1)
    b =  np.array(255*x[i][0].permute(3, 0, 1, 2)[ii, :, :, :].permute(1, 2, 0).cpu().detach().numpy()[:, :, ::-1])
    plt.imshow(cv2.cvtColor(b.astype('uint8'), cv2.COLOR_BGR2RGB))
    plt.axis("off")
plt.show()

how did you make changes to this can you show me step by step i dont understand what you did to make feature map