transformers/docs/source/en
Eduardo Pacheco 3fcfbe7549
Adding SegGPT (#27735)
* First commit

* Improvements

* More improvements

* Converted original checkpoint to HF checkpoint

* Fix style

* Fixed forward

* More improvements

* More improvements

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Remove asserts

* Remove unnecessary attributes

* Changed model name to camel case

* Improve forward doc

* Improve tests

* More improvements

* Fix copies

* Fix doc

* Make SegGptImageProcessor more flexible

* Added few-shot test

* Fix style

* Update READMEs and docs

* Update READMEs

* Make inputs required

* Add SegGptForImageSegmentation

* Make tests pass

* Rename to out_indicies

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Fixed naming convention

* Copying SegGptMlp from modeling_sam.py

* Some minor improvements

* Remove mlp_ratio

* Fix docstrings

* Fixed docstring match

* Objects defined before use

* Storing only patch_size and beta for SegGptLoss

* removed _prepare_inputs method

* Removed modified from headers

* Renamed to output_indicies

* Removed unnecessary einsums

* Update tests/models/seggpt/test_modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update tests/models/seggpt/test_modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update tests/models/seggpt/test_modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Fixing issues

* Raise error as soon as possible

* More fixes

* Fix merge

* Added palette to SegGptImageProcessor

* Fixed typo

* Fixed shape typo

* Added permute before doing palette to class mapping

* Fixed style

* Fixed and added tests

* Fixed docstrings

* Matching SegFormer API for post_processing_semantic_segmentation

* Fixed copies

* Fixed SegGptImageProcessor to handle both binary and RGB masks

* Updated docstrings of SegGptImageProcessor

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update docs/source/en/model_doc/seggpt.md

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/configuration_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/convert_seggpt_to_hf.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update tests/models/seggpt/test_image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update tests/models/seggpt/test_modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Object definitions above & fix style

* Renamed output_indices to intermediate_feature_indices

* Removed unnecessary check on bool_masked_pos

* Loss first in the outputs

* Added validation for do_normalize

* Improved SegGptImageProcessor and added new tests

* Added comment

* Added docstrings to SegGptLoss

* Reimplemented ensemble condition logic in SegGptEncoder

* Update src/transformers/models/seggpt/__init__.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/seggpt/convert_seggpt_to_hf.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Update src/transformers/models/seggpt/configuration_seggpt.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Updated docstrings to use post_process_semantic_segmentation

* Fixed typo on docstrings

* moved pixel values test to test_image_processing_seggpt

* Addressed comments

* Update src/transformers/models/seggpt/configuration_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/image_processing_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/configuration_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Updated docstrings for SegGptLoss

* Address comments

* Added SegGpt example to model docs

* Update src/transformers/models/seggpt/modeling_seggpt.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* moved patchify and unpatchify

* Rename checkpoint

* Renamed intermediate_features to intermediate_hidden_states for consistency

* Update src/transformers/models/seggpt/configuration_seggpt.py

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* Replaced post_process_masks for post_process_semantic_segmentation in the docs

---------

Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
Co-authored-by: Niels <niels.rogge1@gmail.com>
Co-authored-by: Eduardo Pacheco <eduardo.pacheco@limehome.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2024-02-26 18:17:19 +00:00
..
internal Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
main_classes Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
model_doc Adding SegGPT (#27735) 2024-02-26 18:17:19 +00:00
tasks [ gemma] Adds support for Gemma 💎 (#29167) 2024-02-21 14:21:28 +01:00
_config.py [Styling] stylify using ruff (#27144) 2023-11-16 17:43:19 +01:00
_redirects.yml Extended semantic segmentation to image segmentation (#27039) 2023-11-23 15:58:21 +00:00
_toctree.yml Adding SegGPT (#27735) 2024-02-26 18:17:19 +00:00
accelerate.md Fix typos (#25936) 2023-09-04 11:15:12 +01:00
add_new_model.md [Docs] Fix broken links and syntax issues (#28918) 2024-02-08 14:13:35 -08:00
add_new_pipeline.md Fix broken link on page (#28451) 2024-01-11 09:26:13 -08:00
add_tensorflow_model.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
attention.md [Docs] Fix broken links and syntax issues (#28918) 2024-02-08 14:13:35 -08:00
autoclass_tutorial.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
benchmarks.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
bertology.md Migrate doc files to Markdown. (#24376) 2023-06-20 18:07:47 -04:00
big_models.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
chat_templating.md Add chat support to text generation pipeline (#28945) 2024-02-16 16:41:01 +00:00
community.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
contributing.md Enable doc in Spanish (#16518) 2022-04-04 10:25:46 -04:00
create_a_model.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
custom_models.md [Docs] Add language identifiers to fenced code blocks (#28955) 2024-02-12 10:48:31 -08:00
custom_tools.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
debugging.md [Docs] Fix spelling and grammar mistakes (#28825) 2024-02-02 08:45:00 +01:00
deepspeed.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
fast_tokenizers.md Migrate doc files to Markdown. (#24376) 2023-06-20 18:07:47 -04:00
fsdp.md [docs] Trainer docs (#28145) 2023-12-20 10:37:23 -08:00
generation_strategies.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
glossary.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
hf_quantizer.md [docs] HfQuantizer (#28820) 2024-02-02 08:22:18 +01:00
hpo_train.md Remove-auth-token (#27060) 2023-11-13 14:20:54 +01:00
index.md Adding SegGPT (#27735) 2024-02-26 18:17:19 +00:00
installation.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
llm_tutorial_optimization.md F.scaled_dot_product_attention support (#26572) 2023-12-09 05:38:14 +09:00
llm_tutorial.md Generate: All logits processors are documented and have examples (#27796) 2023-12-07 15:11:35 +00:00
model_memory_anatomy.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
model_sharing.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
model_summary.md Migrate doc files to Markdown. (#24376) 2023-06-20 18:07:47 -04:00
multilingual.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
notebooks.md Enable doc in Spanish (#16518) 2022-04-04 10:25:46 -04:00
pad_truncation.md [Doc] Spanish translation of pad_truncation.md (#27890) 2023-12-08 10:32:18 -08:00
peft.md [Peft] modules_to_save support for peft integration (#27466) 2023-11-14 10:32:57 +01:00
perf_hardware.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
perf_infer_cpu.md [Docs] Fix spelling and grammar mistakes (#28825) 2024-02-02 08:45:00 +01:00
perf_infer_gpu_one.md Fix torch.compile with fullgraph=True when attention_mask input is used (#29211) 2024-02-22 16:40:06 +01:00
perf_torch_compile.md Fix rendering for torch.compile() docs (#25432) 2023-08-10 13:25:00 +02:00
perf_train_cpu_many.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
perf_train_cpu.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
perf_train_gpu_many.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
perf_train_gpu_one.md Fix torch.compile with fullgraph=True when attention_mask input is used (#29211) 2024-02-22 16:40:06 +01:00
perf_train_special.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
perf_train_tpu_tf.md Migrate doc files to Markdown. (#24376) 2023-06-20 18:07:47 -04:00
performance.md [docs] Update CPU/GPU inference docs (#26881) 2023-10-31 09:44:51 -07:00
perplexity.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
philosophy.md [docs] fixed links with 404 (#27327) 2023-11-06 19:45:03 +00:00
pipeline_tutorial.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
pipeline_webserver.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
pr_checks.md [Docs] Fix spelling and grammar mistakes (#28825) 2024-02-02 08:45:00 +01:00
preprocessing.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
quantization.md Add training version check for AQLM quantizer. (#29142) 2024-02-21 17:09:36 +01:00
quicktour.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
run_scripts.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
sagemaker.md [docs] fixed links with 404 (#27327) 2023-11-06 19:45:03 +00:00
serialization.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
task_summary.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
tasks_explained.md [docs] Spanish translation of tasks_explained.md (#29224) 2024-02-26 08:18:15 -08:00
testing.md [Docs] Fix spelling and grammar mistakes (#28825) 2024-02-02 08:45:00 +01:00
tf_xla.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
tflite.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
tokenizer_summary.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
torchscript.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
trainer.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
training.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00
transformers_agents.md [doc] Always call it Agents for consistency (#25958) 2023-09-05 12:27:20 +01:00
troubleshooting.md Update all references to canonical models (#29001) 2024-02-16 08:16:58 +01:00