Add Segmentation Ordering for Yolo segmentation #289

aimerib · 2024-09-26T13:57:52Z

Allow yolo segmentation to sort by left-right, top-bottom, largest-smallest, and reverse that order.
Params added to Regional Segmentation Group

Allow yolo segmentation to sort by left-right, top-bottom, largest-smallest, and reverse that order. Params added to Regional Segmentation Group

stupid format-on-save

FurkanGozukara · 2024-09-26T14:05:21Z

thank you so much @aimerib. what will be the new sorting command for this

e.g. modifying this one for only inpainting maximum segment

<segment:yolo-face_yolov9c.pt-1,0.6,0.5>

aimerib · 2024-09-26T14:08:20Z

The command stays the same, and under your parameters list, you should have a Regional Prompting group that you can expand. If you want to segment only the largest found face, toggle on sorting segment, select largest-smallest, and that's it. It will also allow you to sort left-right, top-bottom, and reverse that too.

aimerib · 2024-09-26T14:08:58Z

actually: <segment:yolo-face_yolov9c.pt,0.6,0.5> don't pass an index. it will ignore it anyways.

FurkanGozukara · 2024-09-26T14:10:55Z

actually: <segment:yolo-face_yolov9c.pt,0.6,0.5> don't pass an index. it will ignore it anyways.

but i want to only inpaint first face is that not possible?

aimerib · 2024-09-26T14:12:17Z

I thought the goal was to inpaint the largest face, right? This will detect the largest, no matter the position. If you want only the first found face, then you keep the index. If the use-case is different, do you mind giving me a more detailed scenario so I can mimic it locally?

FurkanGozukara · 2024-09-26T14:14:09Z

I thought the goal was to inpaint the largest face, right? This will detect the largest, no matter the position. If you want only the first found face, then you keep the index. If the use-case is different, do you mind giving me a more detailed scenario so I can mimic it locally?

it is like this

lets say it found 3 faces

only inpaint first one sorted by max area

and thank you so much

aimerib · 2024-09-26T14:17:34Z

So, for this scenario:

use your regular <segment:yolo-face_yolov9c.pt,0.6,0.5> (no index), but in the params, go to regional prompting, turn on Segmentation Ordering, and select "largest-smallest", and run your generation. What you described is the exact usecase I wrote this for. It should only pick up your main face in that image above, nothing else necessary.

FurkanGozukara · 2024-09-26T14:19:32Z

So, for this scenario:

use your regular <segment:yolo-face_yolov9c.pt,0.6,0.5> (no index), but in the params, go to regional prompting, turn on Segmentation Ordering, and select "largest-smallest", and run your generation. What you described is the exact usecase I wrote this for. It should only pick up your main face in that image above, nothing else necessary.

Awesome this solves my issue

But what if someone needs to inpaint 2 different person with different prompt what they can do?

aimerib · 2024-09-26T14:20:55Z

I think I mentioned in the closed issue, but my code only returns the first match. There's room for improving on that exact scenario. I figured that implementing just first match initially was a low-risk way to test that this works. Then we can add the sorting to the scenario where the user passes an index as well. I'm shooting for minimal code changes until we validate that this works well and doesn't break anything.

FurkanGozukara · 2024-09-26T14:22:58Z

I think I mentioned in the closed issue, but my code only returns the first match. There's room for improving on that exact scenario. I figured that implementing just first match initially was a low-risk way to test that this works. Then we can add the sorting to the scenario where the user passes an index as well. I'm shooting for minimal code changes until we validate that this works well and doesn't break anything.

Awesome make sense. I am waiting merge to test asap

mcmonkey4eva · 2024-09-26T15:15:22Z

src/BuiltinExtensions/ComfyUIBackend/ExtraNodes/SwarmComfyExtra/SwarmYolo.py

@@ -11,13 +11,17 @@ def INPUT_TYPES(cls):
                "model_name": (folder_paths.get_filename_list("yolov8"), ),
                "index": ("INT", { "default": 0, "min": 0, "max": 256, "step": 1 }),
            },
+            "optional": {
+                "sort_order": (["left-right", "top-bottom", "largest-smallest", "default"], ),


heck is "default"?

should I change that to none? Or just add a blurb that says "default - if an index is passed, segment the index, if no index is passed, segment all found masks" or something similar?

Basically default is, just do what this would do if nothing was set. Maybe that's redundant because if not toggled nothing is passed? I'm open to suggestions on proper wording.

there is no "default", there's some form of order, always. the code before this PR was explicitly always left-to-right

Then I will simply set left-right as the "default" and remove default as an option. That will better represent the logic that already exists. Makes things easier that way, and less confusing.

mcmonkey4eva · 2024-09-26T15:16:49Z

src/BuiltinExtensions/ComfyUIBackend/ExtraNodes/SwarmComfyExtra/SwarmYolo.py

@@ -57,6 +69,32 @@ def seg(self, image, model_name, index):
            masks = masks[sortedindices]


the sorting code in this function appears to be unmodified? Why is your code not editing the one thing it's meant to edit?

The idea here is that if you used sorting segment, in this current implemention, it ignores the index, and return the first mask after the sort. So the largest (or smallest), top-most (bottom-most), etc. If no sorting is used, then the normal behavior as it used to be is used. I was focusing on @FurkanGozukara usecase for testing this sorting logic, but it wouldn't be hard to make it so you can sort, and also pass and index, so getting the second largest segment, for example.

The idea here is that if you used sorting segment, in this current implemention, it ignores the index, and return the first mask after the sort. So the largest (or smallest), top-most (bottom-most), etc. If no sorting is used, then the normal behavior as it used to be is used. I was focusing on @FurkanGozukara usecase for testing this sorting logic, but it wouldn't be hard to make it so you can sort, and also pass and index, so getting the second largest segment, for example.

i think this would be best case so people can both inpaint with any index with any prompt and still can sort by largest

There's literally existing sort logic here, just. Replace it with customizable sorting. Furkan's case is already covered, it just sorts in the wrong order for what he wants

mcmonkey4eva · 2024-09-26T15:17:04Z

src/BuiltinExtensions/ComfyUIBackend/ExtraNodes/SwarmComfyExtra/SwarmYolo.py

@@ -40,6 +44,14 @@ def seg(self, image, model_name, index):
        else:
            masks = masks.data.cpu()
        masks = torch.nn.functional.interpolate(masks.unsqueeze(1), size=(image.shape[1], image.shape[2]), mode="bilinear").squeeze(1)
+
+        if sort_order != "default":
+            boxes = results[0].boxes


most yolo models don't have boxes

ugh... thanks for the tip. I'll figure out a clean way to handle that scenario.

Again literally just use the existing sorting logic instead of building from scratch, it already accounts for different yolo model variants

mcmonkey4eva · 2024-09-26T15:17:42Z

src/Text2Image/T2IParamTypes.cs

+        SegmentationSortOrder = Register<string>(new("Segmentation Sort Order", "How to sort segments when using '<segment:yolo->' syntax.\nleft-right, top-bottom, largest-smallest, or by-name.\nBy-name requires a pre-processing step to remap segment IDs to a consistent order.",
+            "default", Toggleable: true, IgnoreIf: "default", GetValues: _ => ["left-right", "top-bottom", "largest-smallest", "default"], Group: GroupRegionalPrompting, OrderPriority: 4
+            ));
+        ReverseSegmentationOrder = Register<bool>(new("Reverse Segmentation Order", "If checked, reverses the order of segments when using '<segment:yolo->' syntax.\nOnly applies if 'Segmentation Sort Order' is enabled. When enabled, 'left-right' becomes right-left, 'top-bottom' becomes bottom-top, and 'largest-smallest' becomes smallest-largest.",


this could just be integrated into the first parameter options rather than being separate. less confusing that way too

So first parameter options become: ["left-right", "right-left", "top-bottom", "bottom-top", "largest-smallest", "smallest-largest"] and lose the param for reverting?

… supports indexes

abaddouh · 2024-09-26T21:57:58Z

I believe this new commit should hopefully address most concerns. Primarily, simplify params, support indexes, don't use boxes and use the existing sorting, just expand with custom options.

FurkanGozukara · 2024-09-27T12:15:17Z

i just locally merged and tested

index works as expected

smallest largest sort works too amazing

aimerib · 2024-09-27T12:19:59Z

I'm not sure when smallest to largest would be helpful, but it made sense to add it as an inverse. Depending on the model you use, it might detect a small face on a piece of bread if you don't setup the threshold correctly. Well, now you could target that face too... hahaha

FurkanGozukara · 2024-09-27T12:36:04Z

ok there is an edge error case - i think when no face is found

2024-09-27 12:34:50.853 [Debug] [ComfyUI-4/STDERR] !!! Exception during processing !!! At least one stride in the given numpy array is negative, and tensors with negative strides are not currently supported. (You can probably work around this by making a copy of your array  with array.copy().) 
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR] Traceback (most recent call last):
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR]   File "/home/Ubuntu/apps/StableSwarmUI/dlbackend/ComfyUI/execution.py", line 323, in execute
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR]     output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR]   File "/home/Ubuntu/apps/StableSwarmUI/dlbackend/ComfyUI/execution.py", line 198, in get_output_data
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR]     return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR]   File "/home/Ubuntu/apps/StableSwarmUI/dlbackend/ComfyUI/execution.py", line 169, in _map_node_over_list
2024-09-27 12:34:50.854 [Warning] [ComfyUI-4/STDERR]     process_inputs(input_dict, i)
2024-09-27 12:34:50.855 [Warning] [ComfyUI-4/STDERR]   File "/home/Ubuntu/apps/StableSwarmUI/dlbackend/ComfyUI/execution.py", line 158, in process_inputs
2024-09-27 12:34:50.855 [Warning] [ComfyUI-4/STDERR]     results.append(getattr(obj, func)(**inputs))
2024-09-27 12:34:50.855 [Warning] [ComfyUI-4/STDERR]   File "/home/Ubuntu/apps/StableSwarmUI/src/BuiltinExtensions/ComfyUIBackend/ExtraNodes/SwarmComfyExtra/SwarmYolo.py", line 48, in seg
2024-09-27 12:34:50.855 [Warning] [ComfyUI-4/STDERR]     sortedindices = torch.tensor(np.ascontiguousarray(sortedindices))
2024-09-27 12:34:50.855 [Warning] [ComfyUI-4/STDERR] ValueError: At least one stride in the given numpy array is negative, and tensors with negative strides are not currently supported. (You can probably work around this by making a copy of your array  with array.copy().) 
2024-09-27 12:34:50.855 [Warning] [ComfyUI-4/STDERR] 
2024-09-27 12:34:50.856 [Debug] [ComfyUI-4/STDERR] Prompt executed in 1.05 seconds
2024-09-27 12:34:50.859 [Debug] Failed to process comfy workflow for inputs T2IParamInput(prompt: close shot photo of ohwx man standing on the moon's surface, surrounded by a breathtaking view of Earth in the sky, the stars glittering in the dark void, wearing a futuristic space suit with chrome accents, sleek aerodynamic design, featuring small blue L..., model: FT_256_images_BS7_5e_01_xFormers-000040, seed: 56941881, steps: 40, cfgscale: 1, aspectratio: 1:1, width: 1024, height: 1024, sampler: ipndm, fluxguidancescale: 4, segmentationsortorder: largest-smallest, automaticvae: True, preferreddtype: default, negativeprompt: ) with raw workflow { "4": { "class_type": "UNETLoader", "inputs": { "unet_name": "FT_256_images_BS7_5e_01_xFormers-000040.safetensors", "weight_dtype": "default" } }, "100": { "class_type": "DualCLIPLoader", "inputs": { "clip_name1": "t5xxl_enconly.safetensors", "clip_name2": "clip_l.safetensors", "type": "flux" } }, "101": { "class_type": "VAELoader", "inputs": { "vae_name": "ae.safetensors" } }, "5": { "class_type": "EmptySD3LatentImage", "inputs": { "batch_size": 1, "height": 1024, "width": 1024 } }, "6": { "class_type": "SwarmClipTextEncodeAdvanced", "inputs": { "clip": [ "100", 0 ], "steps": 40, "prompt": "close shot photo of ohwx man standing on the moon's surface, surrounded by a breathtaking view of Earth in the sky, the stars glittering in the dark void, wearing a futuristic space suit with chrome accents, sleek aerodynamic design, featuring small blu...", "width": 1536, "height": 1536, "target_width": 1024, "target_height": 1024, "guidance": 4 } }, "7": { "class_type": "SwarmClipTextEncodeAdvanced", "inputs": { "clip": [ "100", 0 ], "steps": 40, "prompt": "", "width": 832, "height": 832, "target_width": 1024, "target_height": 1024, "guidance": 4 } }, "10": { "class_type": "SwarmKSampler", "inputs": { "model": [ "4", 0 ], "noise_seed": 56941881, "steps": 40, "cfg": 1, "sampler_name": "ipndm", "scheduler": "simple", "positive": [ "6", 0 ], "negative": [ "7", 0 ], "latent_image": [ "5", 0 ], "start_at_step": 0, "end_at_step": 10000, "return_with_leftover_noise": "disable", "add_noise": "enable", "control_after_generate": "fixed", "var_seed": 0, "var_seed_strength": 0, "sigma_min": -1, "sigma_max": -1, "rho": 7, "previews": "default", "tile_sample": False, "tile_size": 1024 } }, "8": { "class_type": "VAEDecode", "inputs": { "vae": [ "101", 0 ], "samples": [ "10", 0 ] } }, "102": { "class_type": "SwarmYoloDetection", "inputs": { "image": [ "8", 0 ], "model_name": "face_yolov9c.pt", "index": 1, "sort_order": "largest-smallest" } }, "103": { "class_type": "SwarmMaskBlur", "inputs": { "mask": [ "102", 0 ], "blur_radius": 10, "sigma": 1 } }, "104": { "class_type": "GrowMask", "inputs": { "mask": [ "103", 0 ], "expand": 16, "tapered_corners": True } }, "105": { "class_type": "SwarmMaskThreshold", "inputs": { "mask": [ "104", 0 ], "min": 0.01, "max": 1 } }, "106": { "class_type": "SwarmMaskBounds", "inputs": { "mask": [ "105", 0 ], "grow": 8 } }, "107": { "class_type": "SwarmImageCrop", "inputs": { "image": [ "8", 0 ], "x": [ "106", 0 ], "y": [ "106", 1 ], "width": [ "106", 2 ], "height": [ "106", 3 ] } }, "108": { "class_type": "CropMask", "inputs": { "mask": [ "105", 0 ], "x": [ "106", 0 ], "y": [ "106", 1 ], "width": [ "106", 2 ], "height": [ "106", 3 ] } }, "109": { "class_type": "SwarmImageScaleForMP", "inputs": { "image": [ "107", 0 ], "width": 1024, "height": 1024, "can_shrink": True } }, "110": { "class_type": "VAEEncode", "inputs": { "vae": [ "101", 0 ], "pixels": [ "109", 0 ] } }, "111": { "class_type": "SetLatentNoiseMask", "inputs": { "samples": [ "110", 0 ], "mask": [ "108", 0 ] } }, "112": { "class_type": "DifferentialDiffusion", "inputs": { "model": [ "4", 0 ] } }, "113": { "class_type": "SwarmClipTextEncodeAdvanced", "inputs": { "clip": [ "100", 0 ], "steps": 40, "prompt": "photo of ohwx man", "width": 1536, "height": 1536, "target_width": 1024, "target_height": 1024, "guidance": 4 } }, "114": { "class_type": "SwarmClipTextEncodeAdvanced", "inputs": { "clip": [ "100", 0 ], "steps": 40, "prompt": "", "width": 832, "height": 832, "target_width": 1024, "target_height": 1024, "guidance": 4 } }, "115": { "class_type": "SwarmKSampler", "inputs": { "model": [ "4", 0 ], "noise_seed": 56941883, "steps": 40, "cfg": 1, "sampler_name": "ipndm", "scheduler": "simple", "positive": [ "113", 0 ], "negative": [ "114", 0 ], "latent_image": [ "111", 0 ], "start_at_step": 9, "end_at_step": 10000, "return_with_leftover_noise": "disable", "add_noise": "enable", "control_after_generate": "fixed", "var_seed": 0, "var_seed_strength": 0, "sigma_min": -1, "sigma_max": -1, "rho": 7, "previews": "default", "tile_sample": False, "tile_size": 1024 } }, "116": { "class_type": "VAEDecode", "inputs": { "vae": [ "101", 0 ], "samples": [ "115", 0 ] } }, "117": { "class_type": "ImageScale", "inputs": { "image": [ "116", 0 ], "width": [ "106", 2 ], "height": [ "106", 3 ], "upscale_method": "bilinear", "crop": "disabled" } }, "118": { "class_type": "ThresholdMask", "inputs": { "mask": [ "108", 0 ], "value": 0.001 } }, "119": { "class_type": "ImageCompositeMasked", "inputs": { "destination": [ "8", 0 ], "source": [ "117", 0 ], "mask": [ "118", 0 ], "x": [ "106", 0 ], "y": [ "106", 1 ], "resize_source": False } }, "9": { "class_type": "SwarmSaveImageWS", "inputs": { "images": [ "119", 0 ], "bit_depth": "8bit" } } }
2024-09-27 12:34:50.859 [Debug] Refused to generate image for local: ComfyUI execution error: At least one stride in the given numpy array is negative, and tensors with negative strides are not currently supported. (You can probably work around this by making a copy of your array  with array.copy().)

aimerib · 2024-09-27T12:37:04Z

Oh! I will fix that right away! Good catch!

FurkanGozukara · 2024-09-27T12:39:26Z

@aimerib also if there is only 1 face will index 1 still work right?

like

<segment:face-1,0.6,0.5>

<segment:yolo-face_yolov9c.pt-1,0.6,0.5>

aimerib · 2024-09-27T12:40:21Z

It should, but I will test it while I'm fixing the other error you found

aimerib · 2024-09-27T12:41:09Z

Basically, we already did ordering before, just always left-right, so using index 1 with only one face found would return that face

aimerib · 2024-09-27T13:02:32Z

@FurkanGozukara what was the specific segment command you used in the prompt that generated that error? I see you used the segmentationordering: "largest-smallest" so I'm trying with that too, but having a hard time hitting the same error

FurkanGozukara · 2024-09-27T13:03:53Z

@aimerib i found another bug

when sorting enabled, it can't find any face

but when it is disabled it can find

here example

photo of ohwx man riding a majestic, muscular white tiger through a dense mystical forest, with trees towering overhead, their twisted branches forming an intricate canopy. The air is filled with glowing fireflies and floating specks of light, creating an ethereal atmosphere. Ohwx wears a regal, intricately embroidered tunic woven with golden threads depicting ancient symbols, a flowing cape with a high collar that shimmers in the dim, magical light. His leather boots have silver buckles, each carved with ornate designs. The tiger's fur glows in the moonlight, and its striking blue eyes mirror Ohwx's vigilant expression. <segment:yolo-face_yolov9c.pt,0.8,0.5>photo of ohwx man

sorting disabled works

sorting enabled

aimerib · 2024-09-27T13:47:20Z

Thank you! I was able to reproduce this error. I've pushed a new commit that should account for the error you were finding. Can you check both scenarios you described above when you have a moment? I really appreciate the help testing these cases!

FurkanGozukara · 2024-09-27T20:50:55Z

@aimerib excellent job

the case that was giving error previously didnt give any error

i am gonna do more testing now hopefully

mcmonkey4eva · 2024-09-28T13:58:32Z

src/BuiltinExtensions/ComfyUIBackend/ExtraNodes/SwarmComfyExtra/SwarmYolo.py

@@ -40,22 +43,46 @@ def seg(self, image, model_name, index):
        else:
            masks = masks.data.cpu()
        masks = torch.nn.functional.interpolate(masks.unsqueeze(1), size=(image.shape[1], image.shape[2]), mode="bilinear").squeeze(1)
+
+        sortedindices = self.sort_masks(masks, sort_order)


this is in the wrong place, it was in the correct place previously, please move it back

I am really sorry, but I am having a super dense moment here. I don't think I see it. Do you mean where it used to exist before, in the block

if index == 0: result = masks[0] for i in range(1, len(masks)): result = torch.max(result, masks[i]) return (result, ) elif index > len(masks): return (torch.zeros_like(masks[0]), ) else: sortedindices = [] ### Here? for mask in masks: sum_x = (torch.sum(mask, dim=0) != 0).to(dtype=torch.int) val = torch.argmax(sum_x).item() sortedindices.append(val) sortedindices = np.argsort(sortedindices) masks = masks[sortedindices] return (masks[index - 1].unsqueeze(0), )

Or where I had it in my previous commit where I was sorting boxes and ignoring masks?
I don't mean to make things difficult, I just have had very very few sleep with the newest phase the kiddo is in, so I would really appreciate a little pointer in the right direction.

Where it was before your PR is the correct place for it to be. Index 0 and index longer than mask count do not require sorting.

Ah, yes, that makes sense. Thank you. I'll fix this.

mcmonkey4eva · 2024-09-28T14:01:28Z

src/Text2Image/T2IParamTypes.cs

@@ -628,6 +628,9 @@ static List<string> listVaes(Session s)
        SaveSegmentMask = Register<bool>(new("Save Segment Mask", "If checked, any usage of '<segment:>' syntax in prompts will save the generated mask in output.",
            "false", IgnoreIf: "false", Group: GroupRegionalPrompting, OrderPriority: 3
            ));
+        SegmentationSortOrder = Register<string>(new("Segmentation Sort Order", "How to sort segments when using '<segment:yolo->' syntax.\nleft-right, top-bottom, bottom-top, largest-smallest, or smallest-largest.\nYou can also use indexes to specify a segment in the given order.\nExmaple: <segment:yolo-face_yolov9c.pt-2> when largest-smallest, will select the second largest face segment.",


you listed the options in description here but excluded right-left

also, indices would be the plural of index, but this should just be use an index

mcmonkey4eva · 2024-09-28T14:03:53Z

src/Text2Image/T2IParamTypes.cs

@@ -628,6 +628,9 @@ static List<string> listVaes(Session s)
        SaveSegmentMask = Register<bool>(new("Save Segment Mask", "If checked, any usage of '<segment:>' syntax in prompts will save the generated mask in output.",
            "false", IgnoreIf: "false", Group: GroupRegionalPrompting, OrderPriority: 3
            ));
+        SegmentationSortOrder = Register<string>(new("Segmentation Sort Order", "How to sort segments when using '<segment:yolo->' syntax.\nleft-right, top-bottom, bottom-top, largest-smallest, or smallest-largest.\nYou can also use indexes to specify a segment in the given order.\nExmaple: <segment:yolo-face_yolov9c.pt-2> when largest-smallest, will select the second largest face segment.",
+            "left-right", Toggleable: true, IgnoreIf: "left-right", GetValues: _ => ["left-right", "right-left", "top-bottom", "bottom-top", "largest-smallest", "smallest-largest"], Group: GroupRegionalPrompting, OrderPriority: 4


OrderPriority 4 is identical to SegmentMaskBlur - also why this is in between mask params?
... also why does the existing code have overlapping order priorities lol.
Probably move this down to 5.5

FurkanGozukara · 2024-09-28T18:13:28Z

by the way i generated over 2k images had no errors with last version

FurkanGozukara · 2024-10-05T00:02:31Z

@mcmonkey4eva can you finalize this? perhaps fix the remaining part? I really would like to show this at next tutorial.

Thank you so much all

aimerib · 2024-10-05T00:45:04Z

@FurkanGozukara I'll work on finishing with the feedback and submit a PR at some point tonight or tomorrow morning at the latest. Sorry about the delay.

FurkanGozukara · 2024-10-10T21:45:34Z

still waiting :/ thank you so much

aimerib · 2024-10-10T21:51:05Z

Yeah, it will be a while longer. There was a massive hurricane here this week, and my family and I had to evacuate out of state. Our town is still full of flooding so it will be a while before I can look at this again. I’m thinking at least after this weekend.

FurkanGozukara · 2024-10-10T21:52:16Z

@aimerib thanks i hope you get better asap without any issues

FurkanGozukara · 2024-10-22T14:27:02Z

shown this in new tutorial i hope gets merged as soon as possible : https://youtu.be/FvpWy1x5etM

aimerib · 2024-10-25T18:08:55Z

@FurkanGozukara I am heading back home this weekend, so either this sunday, or this coming week I will work on the feedback left in this PR and work towards getting it merged. So cool to see this out in the wild already!

FurkanGozukara · 2024-10-25T21:08:59Z

@aimerib awesome ty looking forward to it

FurkanGozukara · 2024-11-01T00:52:35Z

@mcmonkey4eva perhaps you could complete this? I am about to make a video about inpainting , segmentation and yolo masking. Showing this would be great :(

i plan to show a multi face - multi gender image as well like this one

aimerib added 3 commits September 26, 2024 09:50

Add Segmentation Ordering

979b39d

Allow yolo segmentation to sort by left-right, top-bottom, largest-smallest, and reverse that order. Params added to Regional Segmentation Group

remove extra empty line

9010dc2

add removed spaces

12b5bf5

stupid format-on-save

FurkanGozukara mentioned this pull request Sep 26, 2024

Segment only largest finding - very useful to inpaint main face only #287

Closed

mcmonkey4eva reviewed Sep 26, 2024

View reviewed changes

No more boxes, use original sorting with new sort orders implemented,…

4f0030c

… supports indexes

Account for negative strides when converting numpy arrays to tensor

9e014ef

mcmonkey4eva reviewed Sep 28, 2024

View reviewed changes

Small typos and description fixes

976f213

		@@ -57,6 +69,32 @@ def seg(self, image, model_name, index):
		masks = masks[sortedindices]

Add Segmentation Ordering for Yolo segmentation #289

Are you sure you want to change the base?

Add Segmentation Ordering for Yolo segmentation #289

Conversation

aimerib commented Sep 26, 2024

FurkanGozukara commented Sep 26, 2024

aimerib commented Sep 26, 2024

aimerib commented Sep 26, 2024

FurkanGozukara commented Sep 26, 2024

aimerib commented Sep 26, 2024

FurkanGozukara commented Sep 26, 2024

aimerib commented Sep 26, 2024

FurkanGozukara commented Sep 26, 2024

aimerib commented Sep 26, 2024

FurkanGozukara commented Sep 26, 2024

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

abaddouh commented Sep 26, 2024

FurkanGozukara commented Sep 27, 2024

aimerib commented Sep 27, 2024

FurkanGozukara commented Sep 27, 2024

aimerib commented Sep 27, 2024

FurkanGozukara commented Sep 27, 2024

aimerib commented Sep 27, 2024

aimerib commented Sep 27, 2024

aimerib commented Sep 27, 2024

FurkanGozukara commented Sep 27, 2024 • edited Loading

aimerib commented Sep 27, 2024

FurkanGozukara commented Sep 27, 2024

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

FurkanGozukara commented Sep 28, 2024

FurkanGozukara commented Oct 5, 2024

aimerib commented Oct 5, 2024

FurkanGozukara commented Oct 10, 2024

aimerib commented Oct 10, 2024

FurkanGozukara commented Oct 10, 2024

FurkanGozukara commented Oct 22, 2024

aimerib commented Oct 25, 2024

FurkanGozukara commented Oct 25, 2024

FurkanGozukara commented Nov 1, 2024 • edited Loading

FurkanGozukara commented Sep 27, 2024 •

edited

Loading

FurkanGozukara commented Nov 1, 2024 •

edited

Loading