Groma
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
File Explorer
Download Latest Version (.zip)- DATA.md
- EVAL.md
- paradigm.png
- teaser.png
- build.cpython-39.pyc
- collator.cpython-39.pyc
- det_pretrain.py
- vl_finetune.py
- vl_pretrain.py
- grit.cpython-39.pyc
- llava_caption.cpython-39.pyc
- coco.py
- det_data.py
- flickr.py
- grit.py
- groma.py
- llava.py
- lvis.py
- refcoco_cap.py
- refcoco_rec.py
- visual_genome.py
- .DS_Store
- build.py
- collator.py
- conversation.py
- answer_alpaca-13b.jsonl
- answer_bard.jsonl
- answer_gpt35.jsonl
- answer_llama-13b.jsonl
- answer_vicuna-13b.jsonl
- test_sqa_llava_13b_v0.json
- review_alpaca-13b_vicuna-13b.jsonl
- review_bard_vicuna-13b.jsonl
- review_gpt35_vicuna-13b.jsonl
- review_llama-13b_vicuna-13b.jsonl
- alpaca.png
- bard.jpg
- chatgpt.svg
- llama.jpg
- swords_FILL0_wght300_GRAD0_opsz48.svg
- vicuna.jpeg
- index.html
- script.js
- styles.css
- caps_boxes_coco2014_val_80.jsonl
- model.jsonl
- prompt.jsonl
- question.jsonl
- reviewer.jsonl
- rule.json
- eval_cap.py
- eval_gpt_review_visual.py
- eval_lvis.py
- eval_rec.py
- model_refcocog.py
- model_vg.py
- model_vqa.py
- run_ddetr.py
- run_groma.py
- summarize_gpt_review.py
- ddetr.py
- ddetr_transformer.py
- groma.py
- roi_align.py
- extreme_ironing.jpg
- waterview.jpg
- nginx.conf
- README.md
- __init__.py
- cli.py
- controller.py
- gradio_css.py
- gradio_patch.py
- gradio_web_server.py
- model_worker.py
- register_worker.py
- test_message.py
- groma_trainer.py
- llama_flash_attn_monkey_patch.py
- train.py
- train_det.py
- train_mem.py
- .DS_Store
- constants.py
- utils.py
- config.yml
- check_installation.py
- config.yml
- feature_request.md
- general_questions.md
- unexpected_report.md
- build.yml
- build_pat.yml
- lint.yml
- publish-to-pypi.yml
- pull_request_template.md
- 1.png
- 2.png
- 3.png
- readthedocs.css
- mmcv-logo.png
- flow_img2toimg1.png
- flow_raw_images.png
- flow_visualization.png
- flow_warp.png
- flow_warp_diff.png
- parallel_progress.gif
- parallel_progress.png
- progress.gif
- progress.png
- qq_group_qrcode.jpg
- wechat_qrcode.jpg
- zhihu_qrcode.jpg
- contributing.md
- pr.md
- mmcv_ops_definition.md
- onnx.md
- onnxruntime_custom_ops.md
- onnxruntime_op.md
- tensorrt_custom_ops.md
- tensorrt_plugin.md
- build.md
- installation.md
- introduction.md
- previous_versions.md
- cnn.md
- config.md
- data_process.md
- io.md
- ops.md
- registry.md
- runner.md
- utils.md
- visualization.md
- api.rst
- compatibility.md
- conf.py
- faq.md
- index.rst
- make.bat
- Makefile
- mmcv-logo.png
- readthedocs.css
- mmcv-logo.png
- contributing.md
- pr.md
- onnx.md
- onnxruntime_custom_ops.md
- onnxruntime_op.md
- tensorrt_custom_ops.md
- tensorrt_plugin.md
- build.md
- installation.md
- introduction.md
- previous_versions.md
- cnn.md
- config.md
- data_process.md
- io.md
- ops.md
- registry.md
- runner.md
- utils.md
- visualization.md
- api.rst
- compatibility.md
- conf.py
- faq.md
- index.rst
- make.bat
- Makefile
- train.py
- __init__.py
- quantization.py
- __init__.py
- activation.py
- context_block.py
- conv.py
- conv2d_adaptive_padding.py
- conv_module.py
- conv_ws.py
- depthwise_separable_conv_module.py
- drop.py
- generalized_attention.py
- hsigmoid.py
- hswish.py
- non_local.py
- norm.py
- padding.py
- plugin.py
- registry.py
- scale.py
- swish.py
- transformer.py
- upsample.py
- wrappers.py
- __init__.py
- flops_counter.py
- fuse_conv_bn.py
- sync_bn.py
- weight_init.py
- __init__.py
- alexnet.py
- builder.py
- resnet.py
- vgg.py
- __init__.py
- test.py
- __init__.py
- base.py
- json_handler.py
- pickle_handler.py
- yaml_handler.py
- __init__.py
- file_client.py
- io.py
- parse.py
- __init__.py
- colorspace.py
- geometric.py
- io.py
- misc.py
- photometric.py
- __init__.py
- symbolic_helper.py
- __init__.py
- info.py
- symbolic.py
- indice.cuh
- reordering.cuh
- active_rotated_filter_cuda_kernel.cuh
- assign_score_withk_cuda_kernel.cuh
- ball_query_cuda_kernel.cuh
- bbox_overlaps_cuda_kernel.cuh
- border_align_cuda_kernel.cuh
- box_iou_rotated_cuda.cuh
- carafe_cuda_kernel.cuh
- carafe_naive_cuda_kernel.cuh
- common_cuda_helper.hpp
- convex_iou_cuda_kernel.cuh
- correlation_cuda.cuh
- deform_conv_cuda_kernel.cuh
- deform_roi_pool_cuda_kernel.cuh
- furthest_point_sample_cuda_kernel.cuh
- gather_points_cuda_kernel.cuh
- group_points_cuda_kernel.cuh
- iou3d_cuda_kernel.cuh
- knn_cuda_kernel.cuh
- masked_conv2d_cuda_kernel.cuh
- min_area_polygons_cuda.cuh
- modulated_deform_conv_cuda_kernel.cuh
- ms_deform_attn_cuda_kernel.cuh
- nms_cuda_kernel.cuh
- nms_rotated_cuda.cuh
- parrots_cudawarpfunction.cuh
- points_in_boxes_cuda_kernel.cuh
- points_in_polygons_cuda_kernel.cuh
- psamask_cuda_kernel.cuh
- riroi_align_rotated_cuda_kernel.cuh
- roi_align_cuda_kernel.cuh
- roi_align_rotated_cuda_kernel.cuh
- roi_pool_cuda_kernel.cuh
- roiaware_pool3d_cuda_kernel.cuh
- roipoint_pool3d_cuda_kernel.cuh
- rotated_feature_align_cuda_kernel.cuh
- scatter_points_cuda_kernel.cuh
- sigmoid_focal_loss_cuda_kernel.cuh
- softmax_focal_loss_cuda_kernel.cuh
- sync_bn_cuda_kernel.cuh
- three_interpolate_cuda_kernel.cuh
- three_nn_cuda_kernel.cuh
- tin_shift_cuda_kernel.cuh
- voxelization_cuda_kernel.cuh
- geometry.h
- indice.h
- maxpool.h
- mp_helper.h
- point2voxel.h
- reordering.h
- helper_kernel.cuh
- helper_launch.h
- tensorview.h
- paramsgrid.h
- prettyprint.h
- pybind11_utils.h
- box_iou_rotated_utils.hpp
- parrots_cpp_helper.hpp
- parrots_cuda_helper.hpp
- pytorch_cpp_helper.hpp
- pytorch_cuda_helper.hpp
- pytorch_device_registry.hpp
- corner_pool.cpp
- deform_conv.cpp
- gridSample.cpp
- modulated_deform_conv.cpp
- nms.cpp
- onnxruntime_register.cpp
- reduce_ops.cpp
- roi_align.cpp
- roi_align_rotated.cpp
- soft_nms.cpp
- corner_pool.h
- deform_conv.h
- grid_sample.h
- modulated_deform_conv.h
- nms.h
- onnxruntime_register.h
- onnxruntime_session_options_config_keys.h
- ort_mmcv_utils.h
- reduce_ops.h
- roi_align.h
- roi_align_rotated.h
- soft_nms.h
- active_rotated_filter.cpp
- active_rotated_filter_parrots.cpp
- active_rotated_filter_pytorch.h
- assign_score_withk.cpp
- assign_score_withk_parrots.cpp
- assign_score_withk_pytorch.h
- ball_query._parrots.cpp
- ball_query.cpp
- ball_query_pytorch.h
- bbox_overlaps.cpp
- bbox_overlaps_parrots.cpp
- bbox_overlaps_pytorch.h
- border_align.cpp
- border_align_parrots.cpp
- border_align_pytorch.h
- box_iou_rotated.cpp
- box_iou_rotated_parrots.cpp
- box_iou_rotated_pytorch.h
- carafe.cpp
- carafe_naive.cpp
- carafe_naive_parrots.cpp
- carafe_naive_pytorch.h
- carafe_parrots.cpp
- carafe_pytorch.h
- contour_expand.cpp
- contour_expand_parrots.cpp
- contour_expand_pytorch.h
- convex_iou.cpp
- convex_iou_parrots.cpp
- convex_iou_pytorch.h
- corner_pool.cpp
- corner_pool_parrots.cpp
- corner_pool_pytorch.h
- correlation.cpp
- correlation_parrots.cpp
- correlation_pytorch.h
- cudabind.cpp
- deform_conv.cpp
- deform_conv_parrots.cpp
- deform_conv_pytorch.h
- deform_roi_pool.cpp
- deform_roi_pool_parrots.cpp
- deform_roi_pool_pytorch.h
- focal_loss.cpp
- focal_loss_parrots.cpp
- focal_loss_pytorch.h
- furthest_point_sample.cpp
- furthest_point_sample_parrots.cpp
- furthest_point_sample_pytorch.h
- fused_bias_leakyrelu.cpp
- fused_bias_parrots.cpp
- gather_points.cpp
- gather_points_parrots.cpp
- gather_points_pytorch.h
- group_points.cpp
- group_points_parrots.cpp
- group_points_pytorch.h
- info.cpp
- iou3d.cpp
- iou3d_parrots.cpp
- iou3d_pytorch.h
- knn.cpp
- knn_parrots.cpp
- knn_pytorch.h
- masked_conv2d.cpp
- masked_conv2d_parrots.cpp
- masked_conv2d_pytorch.h
- min_area_polygons.cpp
- min_area_polygons_parrots.cpp
- min_area_polygons_pytorch.h
- modulated_deform_conv.cpp
- modulated_deform_conv_parrots.cpp
- modulated_deform_conv_pytorch.h
- ms_deform_attn.cpp
- ms_deform_attn_parrots.cpp
- nms.cpp
- nms_parrots.cpp
- nms_pytorch.h
- nms_rotated.cpp
- pixel_group.cpp
- pixel_group_parrots.cpp
- pixel_group_pytorch.h
- points_in_boxes.cpp
- points_in_boxes_parrots.cpp
- points_in_boxes_pytorch.h
- points_in_polygons.cpp
- points_in_polygons_parrots.cpp
- points_in_polygons_pytorch.h
- psamask.cpp
- psamask_parrots.cpp
- psamask_pytorch.h
- riroi_align_rotated.cpp
- riroi_align_rotated_parrots.cpp
- riroi_align_rotated_pytorch.h
- roi_align.cpp
- roi_align_parrots.cpp
- roi_align_pytorch.h
- roi_align_rotated.cpp
- roi_align_rotated_parrots.cpp
- roi_align_rotated_pytorch.h
- roi_pool.cpp
- roi_pool_parrots.cpp
- roi_pool_pytorch.h
- roiaware_pool3d.cpp
- roiaware_pool3d_parrots.cpp
- roiaware_pool3d_pytorch.h
- roipoint_pool3d.cpp
- roipoint_pool3d_parrots.cpp
- roipoint_pool3d_pytorch.h
- rotated_feature_align.cpp
- rotated_feature_align_parrots.cpp
- rotated_feature_align_pytorch.h
- sync_bn.cpp
- sync_bn_parrots.cpp
- sync_bn_pytorch.h
- three_interpolate.cpp
- three_interpolate_parrots.cpp
- three_interpolate_pytorch.h
- three_nn.cpp
- three_nn_parrots.cpp
- three_nn_pytorch.h
- tin_shift.cpp
- tin_shift_parrots.cpp
- tin_shift_pytorch.h
- upfirdn2d.cpp
- upfirdn2d_parrots.cpp
- voxelization.cpp
- voxelization_parrots.cpp
- voxelization_pytorch.h
- active_rotated_filter.cpp
- box_iou_rotated.cpp
- deform_conv.cpp
- modulated_deform_conv.cpp
- nms.cpp
- nms_rotated.cpp
- pixel_group.cpp
- points_in_boxes.cpp
- psamask.cpp
- roi_align.cpp
- roi_align_rotated.cpp
- sparse_indice.cpp
- sparse_maxpool.cpp
- sparse_reordering.cpp
- voxelization.cpp
- active_rotated_filter_cuda.cu
- assign_score_withk_cuda.cu
- ball_query_cuda.cu
- bbox_overlaps_cuda.cu
- border_align_cuda.cu
- box_iou_rotated_cuda.cu
- carafe_cuda.cu
- carafe_naive_cuda.cu
- convex_iou.cu
- correlation_cuda.cu
- cudabind.cpp
- deform_conv_cuda.cu
- deform_roi_pool_cuda.cu
- focal_loss_cuda.cu
- furthest_point_sample_cuda.cu
- fused_bias_leakyrelu_cuda.cu
- fused_spconv_ops_cuda.cu
- gather_points_cuda.cu
- group_points_cuda.cu
- iou3d_cuda.cu
- knn_cuda.cu
- masked_conv2d_cuda.cu
- min_area_polygons.cu
- modulated_deform_conv_cuda.cu
- ms_deform_attn_cuda.cu
- nms_cuda.cu
- nms_rotated_cuda.cu
- points_in_boxes_cuda.cu
- points_in_polygons_cuda.cu
- psamask_cuda.cu
- riroi_align_rotated_cuda.cu
- roi_align_cuda.cu
- roi_align_rotated_cuda.cu
- roi_pool_cuda.cu
- roiaware_pool3d_cuda.cu
- roipoint_pool3d_cuda.cu
- rotated_feature_align_cuda.cu
- scatter_points_cuda.cu
- sparse_indice.cu
- sparse_maxpool.cu
- sparse_pool_ops_cuda.cu
- sparse_reordering.cu
- spconv_ops_cuda.cu
- sync_bn_cuda.cu
- three_interpolate_cuda.cu
- three_nn_cuda.cu
- tin_shift_cuda.cu
- upfirdn2d_kernel.cu
- voxelization_cuda.cu
- active_rotated_filter.cpp
- assign_score_withk.cpp
- ball_query.cpp
- bbox_overlaps.cpp
- border_align.cpp
- box_iou_rotated.cpp
- carafe.cpp
- carafe_naive.cpp
- contour_expand.cpp
- convex_iou.cpp
- corner_pool.cpp
- correlation.cpp
- deform_conv.cpp
- deform_roi_pool.cpp
- focal_loss.cpp
- furthest_point_sample.cpp
- fused_bias_leakyrelu.cpp
- fused_spconv_ops.cpp
- gather_points.cpp
- group_points.cpp
- info.cpp
- iou3d.cpp
- knn.cpp
- masked_conv2d.cpp
- min_area_polygons.cpp
- modulated_deform_conv.cpp
- ms_deform_attn.cpp
- nms.cpp
- nms_rotated.cpp
- pixel_group.cpp
- points_in_boxes.cpp
- points_in_polygons.cpp
- psamask.cpp
- pybind.cpp
- riroi_align_rotated.cpp
- roi_align.cpp
- roi_align_rotated.cpp
- roi_pool.cpp
- roiaware_pool3d.cpp
- roipoint_pool3d.cpp
- rotated_feature_align.cpp
- scatter_points.cpp
- sparse_pool_ops.cpp
- spconv_ops.cpp
- spconv_utils.h
- sync_bn.cpp
- three_interpolate.cpp
- three_nn.cpp
- tin_shift.cpp
- upfirdn2d.cpp
- voxelization.cpp
- trt_corner_pool.cpp
- trt_corner_pool_kernel.cu
- trt_cuda_helper.cu
- trt_cummaxmin.cpp
- trt_cummaxmin_kernel.cu
- trt_deform_conv.cpp
- trt_deform_conv_kernel.cu
- trt_grid_sampler.cpp
- trt_grid_sampler_kernel.cu
- trt_instance_norm.cpp
- trt_modulated_deform_conv.cpp
- trt_modulated_deform_conv_kernel.cu
- trt_nms.cpp
- trt_nms_kernel.cu
- trt_plugin.cpp
- trt_roi_align.cpp
- trt_roi_align_kernel.cu
- trt_scatternd.cpp
- trt_scatternd_kernel.cu
- trt_corner_pool.hpp
- trt_cuda_helper.cuh
- trt_cummaxmin.hpp
- trt_deform_conv.hpp
- trt_grid_sampler.hpp
- trt_instance_norm.hpp
- trt_modulated_deform_conv.hpp
- trt_nms.hpp
- trt_plugin.hpp
- trt_plugin_helper.hpp
- trt_roi_align.hpp
- trt_scatternd.hpp
- trt_serialize.hpp
- README.md
- __init__.py
- active_rotated_filter.py
- assign_score_withk.py
- ball_query.py
- bbox.py
- border_align.py
- box_iou_rotated.py
- carafe.py
- cc_attention.py
- contour_expand.py
- convex_iou.py
- corner_pool.py
- correlation.py
- deform_conv.py
- deform_roi_pool.py
- deprecated_wrappers.py
- focal_loss.py
- furthest_point_sample.py
- fused_bias_leakyrelu.py
- gather_points.py
- group_points.py
- info.py
- iou3d.py
- knn.py
- masked_conv.py
- merge_cells.py
- min_area_polygons.py
- modulated_deform_conv.py
- multi_scale_deform_attn.py
- nms.py
- pixel_group.py
- point_sample.py
- points_in_boxes.py
- points_in_polygons.py
- points_sampler.py
- psa_mask.py
- riroi_align_rotated.py
- roi_align.py
- roi_align_rotated.py
- roi_pool.py
- roiaware_pool3d.py
- roipoint_pool3d.py
- rotated_feature_align.py
- saconv.py
- scatter_points.py
- sparse_conv.py
- sparse_functional.py
- sparse_modules.py
- sparse_ops.py
- sparse_pool.py
- sparse_structure.py
- sync_bn.py
- three_interpolate.py
- three_nn.py
- tin_shift.py
- upfirdn2d.py
- voxelize.py
- __init__.py
- _functions.py
- collate.py
- data_container.py
- data_parallel.py
- distributed.py
- distributed_deprecated.py
- registry.py
- scatter_gather.py
- utils.py
- __init__.py
- base.py
- dvclive.py
- mlflow.py
- neptune.py
- pavi.py
- segmind.py
- tensorboard.py
- text.py
- wandb.py
- __init__.py
- checkpoint.py
- closure.py
- ema.py
- evaluation.py
- hook.py
- iter_timer.py
- lr_updater.py
- memory.py
- momentum_updater.py
- optimizer.py
- profiler.py
- sampler_seed.py
- sync_buffer.py
- __init__.py
- builder.py
- default_constructor.py
- __init__.py
- base_module.py
- base_runner.py
- builder.py
- checkpoint.py
- default_constructor.py
- dist_utils.py
- epoch_based_runner.py
- fp16_utils.py
- iter_based_runner.py
- log_buffer.py
- priority.py
- utils.py
- __init__.py
- init_plugins.py
- preprocess.py
- tensorrt_utils.py
- __init__.py
- config.py
- env.py
- ext_loader.py
- hub.py
- logging.py
- misc.py
- parrots_jit.py
- parrots_wrapper.py
- path.py
- progressbar.py
- registry.py
- seed.py
- testing.py
- timer.py
- trace.py
- version_utils.py
- __init__.py
- io.py
- optflow.py
- processing.py
- __init__.py
- color.py
- image.py
- optflow.py
- __init__.py
- version.py
- build.txt
- docs.txt
- optional.txt
- runtime.txt
- test.txt
- test_build_layers.py
- test_context_block.py
- test_conv2d_adaptive_padding.py
- test_conv_module.py
- test_depthwise_seperable_conv_module.py
- test_flops_counter.py
- test_fuse_conv_bn.py
- test_generalized_attention.py
- test_hsigmoid.py
- test_hswish.py
- test_model_registry.py
- test_non_local.py
- test_revert_syncbn.py
- test_scale.py
- test_swish.py
- test_transformer.py
- test_weight_init.py
- test_wrappers.py
- test_colorspace.py
- test_geometric.py
- test_image_misc.py
- test_io.py
- test_photometric.py
- test_active_rotated_filter.py
- test_assign_score_withk.py
- test_ball_query.py
- test_bbox.py
- test_bilinear_grid_sample.py
- test_border_align.py
- test_box_iou_rotated.py
- test_carafe.py
- test_cc_attention.py
- test_contour_expand.py
- test_convex_iou.py
- test_corner_pool.py
- test_correlation.py
- test_deform_conv.py
- test_deform_roi_pool.py
- test_focal_loss.py
- test_furthest_point_sample.py
- test_fused_bias_leakyrelu.py
- test_gather_points.py
- test_group_points.py
- test_info.py
- test_iou3d.py
- test_knn.py
- test_masked_conv2d.py
- test_merge_cells.py
- test_min_area_polygons.py
- test_modulated_deform_conv.py
- test_ms_deformable_attn.py
- test_nms.py
- test_nms_rotated.py
- test_onnx.py
- test_pixel_group.py
- test_points_in_polygons.py
- test_psa_mask.py
- test_riroi_align_rotated.py
- test_roi_align.py
- test_roi_align_rotated.py
- test_roi_pool.py
- test_roiaware_pool3d.py
- test_roipoint_pool3d.py
- test_rotated_feature_align.py
- test_saconv.py
- test_scatter_points.py
- test_spconv.py
- test_syncbn.py
- test_tensorrt.py
- test_tensorrt_preprocess.py
- test_three_interpolate.py
- test_three_nn.py
- test_tin_shift.py
- test_upfirdn2d.py
- test_voxelization.py
- test_basemodule.py
- test_checkpoint.py
- test_dist_utils.py
- test_eval_hook.py
- test_fp16.py
- test_hooks.py
- test_optimizer.py
- test_runner.py
- test_utils.py
- test_config.py
- test_env.py
- test_hub.py
- test_logging.py
- test_misc.py
- test_parrots_jit.py
- test_path.py
- test_progressbar.py
- test_registry.py
- test_testing.py
- test_timer.py
- test_trace.py
- test_version_utils.py
- test_optflow.py
- test_processing.py
- test_reader.py
- test_arraymisc.py
- test_fileclient.py
- test_fileio.py
- test_load_model_zoo.py
- test_parallel.py
- test_visualization.py
- .dockerignore
- .gitignore
- .owners.yml
- .pre-commit-config.yaml
- .readthedocs.yml
- CITATION.cff
- CONTRIBUTING.md
- Dockerfile
- Jenkinsfile
- LICENSE
- LICENSES.md
- MANIFEST.in
- README.md
- README_zh-CN.md
- requirements.txt
- setup.cfg
- setup.py
- TERMINOLOGY.md
- __init__.cpython-39.pyc
- version.cpython-39.pyc
- __init__.py
- inference.py
- test.py
- train.py
- __init__.cpython-39.pyc
- __init__.cpython-39.pyc
- anchor_generator.cpython-39.pyc
- builder.cpython-39.pyc
- point_generator.cpython-39.pyc
- utils.cpython-39.pyc
- __init__.py
- anchor_generator.py
- builder.py
- point_generator.py
- utils.py
- __init__.cpython-39.pyc
- builder.cpython-39.pyc
- transforms.cpython-39.pyc
- __init__.cpython-39.pyc
- approx_max_iou_assigner.cpython-39.pyc
- assign_result.cpython-39.pyc
- atss_assigner.cpython-39.pyc
- base_assigner.cpython-39.pyc
- center_region_assigner.cpython-39.pyc
- grid_assigner.cpython-39.pyc
- hungarian_assigner.cpython-39.pyc
- mask_hungarian_assigner.cpython-39.pyc
- max_iou_assigner.cpython-39.pyc
- point_assigner.cpython-39.pyc
- region_assigner.cpython-39.pyc
- sim_ota_assigner.cpython-39.pyc
- task_aligned_assigner.cpython-39.pyc
- uniform_assigner.cpython-39.pyc
- __init__.py
- approx_max_iou_assigner.py
- assign_result.py
- atss_assigner.py
- base_assigner.py
- center_region_assigner.py
- grid_assigner.py
- hungarian_assigner.py
- mask_hungarian_assigner.py
- max_iou_assigner.py
- point_assigner.py
- region_assigner.py
- sim_ota_assigner.py
- task_aligned_assigner.py
- uniform_assigner.py
- __init__.cpython-39.pyc
- base_bbox_coder.cpython-39.pyc
- bucketing_bbox_coder.cpython-39.pyc
- delta_xywh_bbox_coder.cpython-39.pyc
- distance_point_bbox_coder.cpython-39.pyc
- legacy_delta_xywh_bbox_coder.cpython-39.pyc
- pseudo_bbox_coder.cpython-39.pyc
- tblr_bbox_coder.cpython-39.pyc
- yolo_bbox_coder.cpython-39.pyc
- __init__.py
- base_bbox_coder.py
- bucketing_bbox_coder.py
- delta_xywh_bbox_coder.py
- distance_point_bbox_coder.py
- legacy_delta_xywh_bbox_coder.py
- pseudo_bbox_coder.py
- tblr_bbox_coder.py
- yolo_bbox_coder.py
- __init__.cpython-39.pyc
- builder.cpython-39.pyc
- iou2d_calculator.cpython-39.pyc
- __init__.py
- builder.py
- iou2d_calculator.py
- __init__.cpython-39.pyc
- builder.cpython-39.pyc
- match_cost.cpython-39.pyc
- __init__.py
- builder.py
- match_cost.py
- __init__.cpython-39.pyc
- base_sampler.cpython-39.pyc
- combined_sampler.cpython-39.pyc
- instance_balanced_pos_sampler.cpython-39.pyc
- iou_balanced_neg_sampler.cpython-39.pyc
- mask_pseudo_sampler.cpython-39.pyc
- mask_sampling_result.cpython-39.pyc
- ohem_sampler.cpython-39.pyc
- pseudo_sampler.cpython-39.pyc
- random_sampler.cpython-39.pyc
- sampling_result.cpython-39.pyc
- score_hlr_sampler.cpython-39.pyc
- __init__.py
- base_sampler.py
- combined_sampler.py
- instance_balanced_pos_sampler.py
- iou_balanced_neg_sampler.py
- mask_pseudo_sampler.py
- mask_sampling_result.py
- ohem_sampler.py
- pseudo_sampler.py
- random_sampler.py
- sampling_result.py
- score_hlr_sampler.py
- __init__.py
- builder.py
- demodata.py
- transforms.py
- __init__.cpython-39.pyc
- general_data.cpython-39.pyc
- instance_data.cpython-39.pyc
- __init__.py
- general_data.py
- instance_data.py
- __init__.cpython-39.pyc
- bbox_overlaps.cpython-39.pyc
- class_names.cpython-39.pyc
- eval_hooks.cpython-39.pyc
- mean_ap.cpython-39.pyc
- panoptic_utils.cpython-39.pyc
- recall.cpython-39.pyc
- __init__.py
- bbox_overlaps.py
- class_names.py
- eval_hooks.py
- mean_ap.py
- panoptic_utils.py
- recall.py
- __init__.py
- model_wrappers.py
- onnx_helper.py
- pytorch2onnx.py
- __init__.cpython-39.pyc
- checkloss_hook.cpython-39.pyc
- ema.cpython-39.pyc
- set_epoch_info_hook.cpython-39.pyc
- sync_norm_hook.cpython-39.pyc
- sync_random_size_hook.cpython-39.pyc
- yolox_lrupdater_hook.cpython-39.pyc
- yolox_mode_switch_hook.cpython-39.pyc
- __init__.py
- checkloss_hook.py
- ema.py
- set_epoch_info_hook.py
- sync_norm_hook.py
- sync_random_size_hook.py
- yolox_lrupdater_hook.py
- yolox_mode_switch_hook.py
- __init__.cpython-39.pyc
- mask_target.cpython-39.pyc
- structures.cpython-39.pyc
- utils.cpython-39.pyc
- __init__.py
- mask_target.py
- structures.py
- utils.py
- __init__.cpython-39.pyc
- bbox_nms.cpython-39.pyc
- matrix_nms.cpython-39.pyc
- merge_augs.cpython-39.pyc
- __init__.py
- bbox_nms.py
- matrix_nms.py
- merge_augs.py
- __init__.cpython-39.pyc
- dist_utils.cpython-39.pyc
- misc.cpython-39.pyc
- __init__.py
- dist_utils.py
- misc.py
- __init__.cpython-39.pyc
- image.cpython-39.pyc
- palette.cpython-39.pyc
- __init__.py
- image.py
- palette.py
- __init__.py
- __init__.cpython-39.pyc
- builder.cpython-39.pyc
- cityscapes.cpython-39.pyc
- coco.cpython-39.pyc
- coco_panoptic.cpython-39.pyc
- custom.cpython-39.pyc
- dataset_wrappers.cpython-39.pyc
- deepfashion.cpython-39.pyc
- lvis.cpython-39.pyc
- objects365.cpython-39.pyc
- openimages.cpython-39.pyc
- utils.cpython-39.pyc
- voc.cpython-39.pyc
- wider_face.cpython-39.pyc
- xml_style.cpython-39.pyc
- __init__.cpython-39.pyc
- coco_api.cpython-39.pyc
- panoptic_evaluation.cpython-39.pyc
- __init__.py
- coco_api.py
- panoptic_evaluation.py
- __init__.cpython-39.pyc
- auto_augment.cpython-39.pyc
- compose.cpython-39.pyc
- formatting.cpython-39.pyc
- instaboost.cpython-39.pyc
- loading.cpython-39.pyc
- test_time_aug.cpython-39.pyc
- transforms.cpython-39.pyc
- __init__.py
- auto_augment.py
- compose.py
- formating.py
- formatting.py
- instaboost.py
- loading.py
- test_time_aug.py
- transforms.py
- __init__.cpython-39.pyc
- distributed_sampler.cpython-39.pyc
- group_sampler.cpython-39.pyc
- infinite_sampler.cpython-39.pyc
- __init__.py
- distributed_sampler.py
- group_sampler.py
- infinite_sampler.py
- __init__.py
- builder.py
- cityscapes.py
- coco.py
- coco_panoptic.py
- custom.py
- dataset_wrappers.py
- deepfashion.py
- lvis.py
- objects365.py
- openimages.py
- utils.py
- voc.py
- wider_face.py
- xml_style.py
- __init__.cpython-39.pyc
- builder.cpython-39.pyc
- __init__.cpython-39.pyc
- csp_darknet.cpython-39.pyc
- darknet.cpython-39.pyc
- detectors_resnet.cpython-39.pyc
- detectors_resnext.cpython-39.pyc
- hourglass.cpython-39.pyc
- hrnet.cpython-39.pyc
- mobilenet_v2.cpython-39.pyc
- pvt.cpython-39.pyc
- regnet.cpython-39.pyc
- res2net.cpython-39.pyc
- resnest.cpython-39.pyc
- resnet.cpython-39.pyc
- resnext.cpython-39.pyc
- ssd_vgg.cpython-39.pyc
- swin.cpython-39.pyc
- trident_resnet.cpython-39.pyc
- __init__.py
- csp_darknet.py
- darknet.py
- detectors_resnet.py
- detectors_resnext.py
- hourglass.py
- hrnet.py
- mobilenet_v2.py
- pvt.py
- regnet.py
- res2net.py
- resnest.py
- resnet.py
- resnext.py
- ssd_vgg.py
- swin.py
- trident_resnet.py
- __init__.cpython-39.pyc
- anchor_free_head.cpython-39.pyc
- anchor_head.cpython-39.pyc
- atss_head.cpython-39.pyc
- autoassign_head.cpython-39.pyc
- base_dense_head.cpython-39.pyc
- base_mask_head.cpython-39.pyc
- cascade_rpn_head.cpython-39.pyc
- centernet_head.cpython-39.pyc
- centripetal_head.cpython-39.pyc
- corner_head.cpython-39.pyc
- deformable_detr_head.cpython-39.pyc
- dense_test_mixins.cpython-39.pyc
- detr_head.cpython-39.pyc
- embedding_rpn_head.cpython-39.pyc
- fcos_head.cpython-39.pyc
- fovea_head.cpython-39.pyc
- free_anchor_retina_head.cpython-39.pyc
- fsaf_head.cpython-39.pyc
- ga_retina_head.cpython-39.pyc
- ga_rpn_head.cpython-39.pyc
- gfl_head.cpython-39.pyc
- guided_anchor_head.cpython-39.pyc
- lad_head.cpython-39.pyc
- ld_head.cpython-39.pyc
- maskformer_head.cpython-39.pyc
- nasfcos_head.cpython-39.pyc
- paa_head.cpython-39.pyc
- pisa_retinanet_head.cpython-39.pyc
- pisa_ssd_head.cpython-39.pyc
- reppoints_head.cpython-39.pyc
- retina_head.cpython-39.pyc
- retina_sepbn_head.cpython-39.pyc
- rpn_head.cpython-39.pyc
- sabl_retina_head.cpython-39.pyc
- solo_head.cpython-39.pyc
- ssd_head.cpython-39.pyc
- tood_head.cpython-39.pyc
- vfnet_head.cpython-39.pyc
- yolact_head.cpython-39.pyc
- yolo_head.cpython-39.pyc
- yolof_head.cpython-39.pyc
- yolox_head.cpython-39.pyc
- __init__.py
- anchor_free_head.py
- anchor_head.py
- atss_head.py
- autoassign_head.py
- base_dense_head.py
- base_mask_head.py
- cascade_rpn_head.py
- centernet_head.py
- centripetal_head.py
- corner_head.py
- deformable_detr_head.py
- dense_test_mixins.py
- detr_head.py
- embedding_rpn_head.py
- fcos_head.py
- fovea_head.py
- free_anchor_retina_head.py
- fsaf_head.py
- ga_retina_head.py
- ga_rpn_head.py
- gfl_head.py
- guided_anchor_head.py
- lad_head.py
- ld_head.py
- maskformer_head.py
- nasfcos_head.py
- paa_head.py
- pisa_retinanet_head.py
- pisa_ssd_head.py
- reppoints_head.py
- retina_head.py
- retina_sepbn_head.py
- rpn_head.py
- sabl_retina_head.py
- solo_head.py
- ssd_head.py
- tood_head.py
- vfnet_head.py
- yolact_head.py
- yolo_head.py
- yolof_head.py
- yolox_head.py
- __init__.cpython-39.pyc
- atss.cpython-39.pyc
- autoassign.cpython-39.pyc
- base.cpython-39.pyc
- cascade_rcnn.cpython-39.pyc
- centernet.cpython-39.pyc
- cornernet.cpython-39.pyc
- deformable_detr.cpython-39.pyc
- detr.cpython-39.pyc
- fast_rcnn.cpython-39.pyc
- faster_rcnn.cpython-39.pyc
- fcos.cpython-39.pyc
- fovea.cpython-39.pyc
- fsaf.cpython-39.pyc
- gfl.cpython-39.pyc
- grid_rcnn.cpython-39.pyc
- htc.cpython-39.pyc
- kd_one_stage.cpython-39.pyc
- lad.cpython-39.pyc
- mask_rcnn.cpython-39.pyc
- mask_scoring_rcnn.cpython-39.pyc
- maskformer.cpython-39.pyc
- nasfcos.cpython-39.pyc
- paa.cpython-39.pyc
- panoptic_fpn.cpython-39.pyc
- panoptic_two_stage_segmentor.cpython-39.pyc
- point_rend.cpython-39.pyc
- queryinst.cpython-39.pyc
- reppoints_detector.cpython-39.pyc
- retinanet.cpython-39.pyc
- rpn.cpython-39.pyc
- scnet.cpython-39.pyc
- single_stage.cpython-39.pyc
- single_stage_instance_seg.cpython-39.pyc
- solo.cpython-39.pyc
- sparse_rcnn.cpython-39.pyc
- tood.cpython-39.pyc
- trident_faster_rcnn.cpython-39.pyc
- two_stage.cpython-39.pyc
- vfnet.cpython-39.pyc
- yolact.cpython-39.pyc
- yolo.cpython-39.pyc
- yolof.cpython-39.pyc
- yolox.cpython-39.pyc
- __init__.py
- atss.py
- autoassign.py
- base.py
- cascade_rcnn.py
- centernet.py
- cornernet.py
- deformable_detr.py
- detr.py
- fast_rcnn.py
- faster_rcnn.py
- fcos.py
- fovea.py
- fsaf.py
- gfl.py
- grid_rcnn.py
- htc.py
- kd_one_stage.py
- lad.py
- mask_rcnn.py
- mask_scoring_rcnn.py
- maskformer.py
- nasfcos.py
- paa.py
- panoptic_fpn.py
- panoptic_two_stage_segmentor.py
- point_rend.py
- queryinst.py
- reppoints_detector.py
- retinanet.py
- rpn.py
- scnet.py
- single_stage.py
- single_stage_instance_seg.py
- solo.py
- sparse_rcnn.py
- tood.py
- trident_faster_rcnn.py
- two_stage.py
- vfnet.py
- yolact.py
- yolo.py
- yolof.py
- yolox.py
- __init__.cpython-39.pyc
- accuracy.cpython-39.pyc
- ae_loss.cpython-39.pyc
- balanced_l1_loss.cpython-39.pyc
- cross_entropy_loss.cpython-39.pyc
- dice_loss.cpython-39.pyc
- focal_loss.cpython-39.pyc
- gaussian_focal_loss.cpython-39.pyc
- gfocal_loss.cpython-39.pyc
- ghm_loss.cpython-39.pyc
- iou_loss.cpython-39.pyc
- kd_loss.cpython-39.pyc
- mse_loss.cpython-39.pyc
- pisa_loss.cpython-39.pyc
- seesaw_loss.cpython-39.pyc
- smooth_l1_loss.cpython-39.pyc
- utils.cpython-39.pyc
- varifocal_loss.cpython-39.pyc
- __init__.py
- accuracy.py
- ae_loss.py
- balanced_l1_loss.py
- cross_entropy_loss.py
- dice_loss.py
- focal_loss.py
- gaussian_focal_loss.py
- gfocal_loss.py
- ghm_loss.py
- iou_loss.py
- kd_loss.py
- mse_loss.py
- pisa_loss.py
- seesaw_loss.py
- smooth_l1_loss.py
- utils.py
- varifocal_loss.py
- __init__.cpython-39.pyc
- bfp.cpython-39.pyc
- channel_mapper.cpython-39.pyc
- ct_resnet_neck.cpython-39.pyc
- dilated_encoder.cpython-39.pyc
- dyhead.cpython-39.pyc
- fpg.cpython-39.pyc
- fpn.cpython-39.pyc
- fpn_carafe.cpython-39.pyc
- hrfpn.cpython-39.pyc
- nas_fpn.cpython-39.pyc
- nasfcos_fpn.cpython-39.pyc
- pafpn.cpython-39.pyc
- rfp.cpython-39.pyc
- ssd_neck.cpython-39.pyc
- yolo_neck.cpython-39.pyc
- yolox_pafpn.cpython-39.pyc
- __init__.py
- bfp.py
- channel_mapper.py
- ct_resnet_neck.py
- dilated_encoder.py
- dyhead.py
- fpg.py
- fpn.py
- fpn_carafe.py
- hrfpn.py
- nas_fpn.py
- nasfcos_fpn.py
- pafpn.py
- rfp.py
- ssd_neck.py
- yolo_neck.py
- yolox_pafpn.py
- __init__.cpython-39.pyc
- dropblock.cpython-39.pyc
- pixel_decoder.cpython-39.pyc
- __init__.py
- dropblock.py
- pixel_decoder.py
- __init__.cpython-39.pyc
- base_roi_head.cpython-39.pyc
- cascade_roi_head.cpython-39.pyc
- double_roi_head.cpython-39.pyc
- dynamic_roi_head.cpython-39.pyc
- grid_roi_head.cpython-39.pyc
- htc_roi_head.cpython-39.pyc
- mask_scoring_roi_head.cpython-39.pyc
- pisa_roi_head.cpython-39.pyc
- point_rend_roi_head.cpython-39.pyc
- scnet_roi_head.cpython-39.pyc
- sparse_roi_head.cpython-39.pyc
- standard_roi_head.cpython-39.pyc
- test_mixins.cpython-39.pyc
- trident_roi_head.cpython-39.pyc
- __init__.cpython-39.pyc
- bbox_head.cpython-39.pyc
- convfc_bbox_head.cpython-39.pyc
- dii_head.cpython-39.pyc
- double_bbox_head.cpython-39.pyc
- sabl_head.cpython-39.pyc
- scnet_bbox_head.cpython-39.pyc
- __init__.py
- bbox_head.py
- convfc_bbox_head.py
- dii_head.py
- double_bbox_head.py
- sabl_head.py
- scnet_bbox_head.py
- __init__.cpython-39.pyc
- coarse_mask_head.cpython-39.pyc
- dynamic_mask_head.cpython-39.pyc
- fcn_mask_head.cpython-39.pyc
- feature_relay_head.cpython-39.pyc
- fused_semantic_head.cpython-39.pyc
- global_context_head.cpython-39.pyc
- grid_head.cpython-39.pyc
- htc_mask_head.cpython-39.pyc
- mask_point_head.cpython-39.pyc
- maskiou_head.cpython-39.pyc
- scnet_mask_head.cpython-39.pyc
- scnet_semantic_head.cpython-39.pyc
- __init__.py
- coarse_mask_head.py
- dynamic_mask_head.py
- fcn_mask_head.py
- feature_relay_head.py
- fused_semantic_head.py
- global_context_head.py
- grid_head.py
- htc_mask_head.py
- mask_point_head.py
- maskiou_head.py
- scnet_mask_head.py
- scnet_semantic_head.py
- __init__.cpython-39.pyc
- base_roi_extractor.cpython-39.pyc
- generic_roi_extractor.cpython-39.pyc
- single_level_roi_extractor.cpython-39.pyc
- __init__.py
- base_roi_extractor.py
- generic_roi_extractor.py
- single_level_roi_extractor.py
- __init__.cpython-39.pyc
- res_layer.cpython-39.pyc
- __init__.py
- res_layer.py
- __init__.py
- base_roi_head.py
- cascade_roi_head.py
- double_roi_head.py
- dynamic_roi_head.py
- grid_roi_head.py
- htc_roi_head.py
- mask_scoring_roi_head.py
- pisa_roi_head.py
- point_rend_roi_head.py
- scnet_roi_head.py
- sparse_roi_head.py
- standard_roi_head.py
- test_mixins.py
- trident_roi_head.py
- __init__.cpython-39.pyc
- base_semantic_head.cpython-39.pyc
- panoptic_fpn_head.cpython-39.pyc
- __init__.cpython-39.pyc
- base_panoptic_fusion_head.cpython-39.pyc
- heuristic_fusion_head.cpython-39.pyc
- __init__.py
- base_panoptic_fusion_head.py
- heuristic_fusion_head.py
- __init__.py
- base_semantic_head.py
- panoptic_fpn_head.py
- __init__.cpython-39.pyc
- brick_wrappers.cpython-39.pyc
- builder.cpython-39.pyc
- ckpt_convert.cpython-39.pyc
- conv_upsample.cpython-39.pyc
- csp_layer.cpython-39.pyc
- gaussian_target.cpython-39.pyc
- inverted_residual.cpython-39.pyc
- make_divisible.cpython-39.pyc
- misc.cpython-39.pyc
- normed_predictor.cpython-39.pyc
- panoptic_gt_processing.cpython-39.pyc
- positional_encoding.cpython-39.pyc
- res_layer.cpython-39.pyc
- se_layer.cpython-39.pyc
- transformer.cpython-39.pyc
- __init__.py
- brick_wrappers.py
- builder.py
- ckpt_convert.py
- conv_upsample.py
- csp_layer.py
- gaussian_target.py
- inverted_residual.py
- make_divisible.py
- misc.py
- normed_predictor.py
- panoptic_gt_processing.py
- positional_encoding.py
- res_layer.py
- se_layer.py
- transformer.py
- __init__.py
- builder.py
- __init__.cpython-39.pyc
- collect_env.cpython-39.pyc
- contextmanagers.cpython-39.pyc
- logger.cpython-39.pyc
- misc.cpython-39.pyc
- setup_env.cpython-39.pyc
- util_mixins.cpython-39.pyc
- __init__.py
- collect_env.py
- contextmanagers.py
- logger.py
- misc.py
- profiling.py
- setup_env.py
- util_mixins.py
- util_random.py
- .DS_Store
- __init__.py
- version.py
- debug.sh
- det_pretrain.sh
- fsdp_config.json
- vl_finetune.sh
- vl_pretrain.sh
- .gitignore
- LICENSE
- pyproject.toml
- README.md
# Installation Guide
1. Get the code
git clone https://github.com/FoundationVision/Groma
Downloads the entire project code from GitHub to your computer.
cd Groma
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -f mmcv/Dockerfile -t groma .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 groma
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
3. Python
EasyPrerequisites
pip install -r mmcv/requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
python <μ€νν νμΌλͺ
>.py # READMEμμ μ νν μ€ν νμΌλͺ
μ νμΈνμΈμ
Runs the Python script (or module).
If it runs without errors and prints output in the terminal, it worked.
// repository documentation
Was this content helpful?
(0 ratings)