deepgeo_ext_maskrcnn
Project description
DeepGeo Extension :: Mask R-CNN
-
Easy Deep Learning
-
Copyright (c) 2019 InfoLab (Donggun LEE)
-
How to install
pip install deepgeo_ext_maskrcnn
- other version
# 0.0.1 pip install deepgeo_ext_maskrcnn==0.0.1
- requirement
- Python 3.6
pip install deepgeo
- other version
-
How to use
import deepgeo engine = deepgeo.Engine() engine.add_model('maskrcnn_mscoco','maskrcnn','D:/default_config.json') image = deepgeo.Image.Image("image.jpg","D:/Project") image = engine.detect('maskrcnn_mscoco', image) image.draw_annotations(image.get_annotation()) image.save("D:/","test","PNG")
-
default_config.json
{ "BACKBONE": "resnet101", "BACKBONE_STRIDES": [ 4, 8, 16, 32, 64 ], "BATCH_SIZE": 1, "BBOX_STD_DEV": [0.1, 0.1, 0.2, 0.2], "CATEGORY": [ "bg", "person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic_light", "fire_hydrant", "stop_sign", "parking_meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow", "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports_ball", "kite", "baseball_bat", "baseball_glove", "skateboard", "surfboard", "tennis_racket", "bottle", "wine_glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot_dog", "pizza", "donut", "cake", "chair", "couch", "potted_plant", "bed", "dining_table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell_phone", "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy_bear", "hair_drier", "toothbrush" ], "COMPUTE_BACKBONE_SHAPE": null, "DETECTION_MAX_INSTANCES": 100, "DETECTION_MIN_CONFIDENCE": 0.7, "DETECTION_NMS_THRESHOLD": 0.3, "EPOCHS": 1, "FPN_CLASSIF_FC_LAYERS_SIZE": 1024, "GPU_COUNT": 1, "GRADIENT_CLIP_NORM": 5.0, "IMAGES_PER_GPU": 1, "IMAGE_CHANNEL_COUNT": 3, "IMAGE_MAX_DIM": 1024, "IMAGE_META_SIZE": 14, "IMAGE_MIN_DIM": 800, "IMAGE_MIN_SCALE": 0, "IMAGE_PATH": "image", "IMAGE_RESIZE_MODE": "square", "IMAGE_SHAPE": null, "LAYERS": "all", "LEARNING_MOMENTUM": 0.9, "LEARNING_RATE": 0.001, "LOSS_WEIGHTS": { "mrcnn_bbox_loss": 1.0, "mrcnn_class_loss": 1.0, "mrcnn_mask_loss": 1.0, "rpn_bbox_loss": 1.0, "rpn_class_loss": 1.0 }, "MASK_POOL_SIZE": 14, "MASK_SHAPE": [ 28, 28 ], "MAX_GT_INSTANCES": 100, "MEAN_PIXEL": [123.7, 116.8, 103.9], "MEMO": "", "MINI_MASK_SHAPE": [ 56, 56 ], "MODEL_FILE_NAME": "mask_rcnn_coco.h5", "MODEL_PATH":"model", "MODEL_URI":"", "NAME": "MASK_RCNN", "NUM_CLASSES": 80, "POOL_SIZE": 7, "POST_NMS_ROIS_INFERENCE": 1000, "POST_NMS_ROIS_TRAINING": 2000, "PRE_NMS_LIMIT": 6000, "RESULT_TEST_NUM": 100, "ROI_POSITIVE_RATIO": 0.33, "RPN_ANCHOR_RATIOS": [ 0.5, 1, 2 ], "RPN_ANCHOR_SCALES": [ 32, 64, 128, 256, 512 ], "RPN_ANCHOR_STRIDE": 1, "RPN_BBOX_STD_DEV": [0.1,0.1,0.2,0.2], "RPN_NMS_THRESHOLD": 0.7, "RPN_TRAIN_ANCHORS_PER_IMAGE": 256, "STEPS_PER_EPOCH": 1000, "TOP_DOWN_PYRAMID_SIZE": 256, "TRAIN_BN": false, "TRAIN_ROIS_PER_IMAGE": 200, "USE_MINI_MASK": true, "USE_RPN_ROIS": true, "VALIDATION_STEPS": 50, "VERSION": "", "WEIGHT_DECAY": 0.0001 }
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file deepgeo_ext_maskrcnn-0.0.1.tar.gz
.
File metadata
- Download URL: deepgeo_ext_maskrcnn-0.0.1.tar.gz
- Upload date:
- Size: 56.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.6.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | dbd914aaf57f3f5cff1750353acf03d6bba5f39ffd705536ae232c4c2fdd846f |
|
MD5 | 8dc3886e5e2c78b4a4c6665086c7d8e8 |
|
BLAKE2b-256 | 6256d8265a42883d22a29323d1189df3cbc8d52f4ec2844ac6933aa6498ba46e |
File details
Details for the file deepgeo_ext_maskrcnn-0.0.1-py3-none-any.whl
.
File metadata
- Download URL: deepgeo_ext_maskrcnn-0.0.1-py3-none-any.whl
- Upload date:
- Size: 59.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.13.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/41.0.1 requests-toolbelt/0.9.1 tqdm/4.32.2 CPython/3.6.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | fd5b76a4b2e4fc8eba989201c33bdbd395c8c992c838637d4cdba6cbee4c1baf |
|
MD5 | deb127c28bd9a75eaa16a43b1f5c563a |
|
BLAKE2b-256 | 4e45db1e46898d8c6b978dfdf9e7d4f5cd6f5f4339db75fa3567a58f67ab8f4b |