Upload folder using huggingface_hub

Pretrain/README.md

@@ -0,0 +1,69 @@
+---
+license: apache-2.0
+tags:
+- vision
+inference: false
+pipeline_tag: zero-shot-object-detection
+---
+
+# Grounding DINO model (tiny variant)
+
+The Grounding DINO model was proposed in [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://arxiv.org/abs/2303.05499) by Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang. Grounding DINO extends a closed-set object detection model with a text encoder, enabling open-set object detection. The model achieves remarkable results, such as 52.5 AP on COCO zero-shot.
+
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/grouding_dino_architecture.png"
+alt="drawing" width="600"/>
+
+<small> Grounding DINO overview. Taken from the <a href="https://arxiv.org/abs/2303.05499">original paper</a>. </small>
+
+## Intended uses & limitations
+
+You can use the raw model for zero-shot object detection (the task of detecting things in an image out-of-the-box without labeled data).
+
+### How to use
+
+Here's how to use the model for zero-shot object detection:
+
+```python
+import requests
+
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection 
+
+model_id = "IDEA-Research/grounding-dino-tiny"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(device)
+
+image_url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(image_url, stream=True).raw)
+# Check for cats and remote controls
+# VERY important: text queries need to be lowercased + end with a dot
+text = "a cat. a remote control."
+
+inputs = processor(images=image, text=text, return_tensors="pt").to(device)
+with torch.no_grad():
+    outputs = model(**inputs)
+
+results = processor.post_process_grounded_object_detection(
+    outputs,
+    inputs.input_ids,
+    box_threshold=0.4,
+    text_threshold=0.3,
+    target_sizes=[image.size[::-1]]
+)
+```
+
+### BibTeX entry and citation info
+
+```bibtex
+@misc{liu2023grounding,
+      title={Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection}, 
+      author={Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang},
+      year={2023},
+      eprint={2303.05499},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

Pretrain/added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

Pretrain/config.json

@@ -0,0 +1,77 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "GroundingDinoForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": null,
+  "backbone_config": {
+    "depths": [
+      2,
+      2,
+      6,
+      2
+    ],
+    "model_type": "swin",
+    "num_heads": [
+      3,
+      6,
+      12,
+      24
+    ],
+    "out_features": [
+      "stage2",
+      "stage3",
+      "stage4"
+    ],
+    "out_indices": [
+      2,
+      3,
+      4
+    ]
+  },
+  "backbone_kwargs": null,
+  "bbox_cost": 5.0,
+  "bbox_loss_coefficient": 5.0,
+  "class_cost": 1.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_bbox_embed_share": true,
+  "decoder_ffn_dim": 2048,
+  "decoder_layers": 6,
+  "decoder_n_points": 4,
+  "disable_custom_kernels": false,
+  "dropout": 0.1,
+  "embedding_init_target": true,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layers": 6,
+  "encoder_n_points": 4,
+  "focal_alpha": 0.25,
+  "fusion_dropout": 0.0,
+  "fusion_droppath": 0.1,
+  "giou_cost": 2.0,
+  "giou_loss_coefficient": 2.0,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "layer_norm_eps": 1e-05,
+  "max_text_len": 256,
+  "model_type": "grounding-dino",
+  "num_feature_levels": 4,
+  "num_queries": 900,
+  "position_embedding_type": "sine",
+  "positional_embedding_temperature": 20,
+  "query_dim": 4,
+  "text_config": {
+    "model_type": "bert"
+  },
+  "text_enhancer_dropout": 0.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0.dev0",
+  "two_stage": true,
+  "two_stage_bbox_embed_share": false,
+  "use_pretrained_backbone": false,
+  "use_timm_backbone": false
+}

Pretrain/gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Pretrain/preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "GroundingDinoImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "processor_class": "GroundingDinoProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

Pretrain/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96df8170959d691ca6bdbe75676dafe5c37d29e48970a666461f755c4fa707be
+size 684703744

Pretrain/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

Pretrain/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "processor_class": "GroundingDinoProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoints/download_ckpts.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+# Use either wget or curl to download the checkpoints
+CMD="wget"
+#if command -v wget &> /dev/null; then
+#    CMD="wget"
+#elif command -v curl &> /dev/null; then
+#    CMD="curl -L -O"
+#else
+#    echo "Please install wget or curl to download the checkpoints."
+#    exit 1
+#fi
+# Define the URLs for SAM 2 checkpoints
+# SAM2_BASE_URL="https://dl.fbaipublicfiles.com/segment_anything_2/072824"
+# sam2_hiera_t_url="${SAM2_BASE_URL}/sam2_hiera_tiny.pt"
+# sam2_hiera_s_url="${SAM2_BASE_URL}/sam2_hiera_small.pt"
+# sam2_hiera_b_plus_url="${SAM2_BASE_URL}/sam2_hiera_base_plus.pt"
+# sam2_hiera_l_url="${SAM2_BASE_URL}/sam2_hiera_large.pt"
+# Download each of the four checkpoints using wget
+# echo "Downloading sam2_hiera_tiny.pt checkpoint..."
+# $CMD $sam2_hiera_t_url || { echo "Failed to download checkpoint from $sam2_hiera_t_url"; exit 1; }
+# echo "Downloading sam2_hiera_small.pt checkpoint..."
+# $CMD $sam2_hiera_s_url || { echo "Failed to download checkpoint from $sam2_hiera_s_url"; exit 1; }
+# echo "Downloading sam2_hiera_base_plus.pt checkpoint..."
+# $CMD $sam2_hiera_b_plus_url || { echo "Failed to download checkpoint from $sam2_hiera_b_plus_url"; exit 1; }
+# echo "Downloading sam2_hiera_large.pt checkpoint..."
+# $CMD $sam2_hiera_l_url || { echo "Failed to download checkpoint from $sam2_hiera_l_url"; exit 1; }
+# Define the URLs for SAM 2.1 checkpoints
+SAM2p1_BASE_URL="https://dl.fbaipublicfiles.com/segment_anything_2/092824"
+sam2p1_hiera_t_url="${SAM2p1_BASE_URL}/sam2.1_hiera_tiny.pt"
+sam2p1_hiera_s_url="${SAM2p1_BASE_URL}/sam2.1_hiera_small.pt"
+sam2p1_hiera_b_plus_url="${SAM2p1_BASE_URL}/sam2.1_hiera_base_plus.pt"
+sam2p1_hiera_l_url="${SAM2p1_BASE_URL}/sam2.1_hiera_large.pt"
+# SAM 2.1 checkpoints
+echo "Downloading sam2.1_hiera_tiny.pt checkpoint..."
+$CMD $sam2p1_hiera_t_url || { echo "Failed to download checkpoint from $sam2p1_hiera_t_url"; exit 1; }
+
+echo "Downloading sam2.1_hiera_small.pt checkpoint..."
+$CMD $sam2p1_hiera_s_url || { echo "Failed to download checkpoint from $sam2p1_hiera_s_url"; exit 1; }
+
+echo "Downloading sam2.1_hiera_base_plus.pt checkpoint..."
+$CMD $sam2p1_hiera_b_plus_url || { echo "Failed to download checkpoint from $sam2p1_hiera_b_plus_url"; exit 1; }
+
+echo "Downloading sam2.1_hiera_large.pt checkpoint..."
+$CMD $sam2p1_hiera_l_url || { echo "Failed to download checkpoint from $sam2p1_hiera_l_url"; exit 1; }
+#echo "All checkpoints are downloaded successfully."

checkpoints/sam2.1_hiera_base_plus.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2345aede8715ab1d5d31b4a509fb160c5a4af1970f199d9054ccfb746c004c5
+size 323606802

checkpoints/sam2.1_hiera_large.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2647878d5dfa5098f2f8649825738a9345572bae2d4350a2468587ece47dd318
+size 898083611

checkpoints/sam2.1_hiera_small.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1aa6f30de5c92224f8172114de081d104bbd23dd9dc5c58996f0cad5dc4d38
+size 184416285

checkpoints/sam2.1_hiera_tiny.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7402e0d864fa82708a20fbd15bc84245c2f26dff0eb43a4b5b93452deb34be69
+size 156008466

exps/demo/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b03c40259bfbdfc96e490124726ec7db9b2d8e8921f1c68391a9bb29e9ed1220
+size 736657806

gdino_checkpoints/download_ckpts.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+
+# Define the URLs for the checkpoints
+BASE_URL="https://github.com/IDEA-Research/GroundingDINO/releases/download/"
+swint_ogc_url="${BASE_URL}v0.1.0-alpha/groundingdino_swint_ogc.pth"
+swinb_cogcoor_url="${BASE_URL}v0.1.0-alpha2/groundingdino_swinb_cogcoor.pth"
+
+
+
+# Download each of the four checkpoints using wget
+echo "Downloading groundingdino_swint_ogc.pth checkpoint..."
+wget $swint_ogc_url || { echo "Failed to download checkpoint from $swint_ogc_url"; exit 1; }
+
+echo "Downloading groundingdino_swinb_cogcoor.pth checkpoint..."
+wget $swinb_cogcoor_url || { echo "Failed to download checkpoint from $swinb_cogcoor_url"; exit 1; }
+
+echo "All checkpoints are downloaded successfully."

gdino_checkpoints/groundingdino_swinb_cogcoor.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46270f7a822e6906b655b729c90613e48929d0f2bb8b9b76fd10a856f3ac6ab7
+size 938057991

gdino_checkpoints/groundingdino_swint_ogc.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3ca2563c77c69f651d7bd133e97139c186df06231157a64c507099c52bc799
+size 693997677