Merge pull request #23 from visionNoob/issue_22

Initial Commit (#22)

CONTRIBUTING.md

@@ -0,0 +1 @@
+# see https://github.com/keras-team/keras

Untitled.ipynb

@@ -0,0 +1,49 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import keras\n",
+    "import yolk \n",
+    "\n",
+    "voc_train, voc_valid = yolk.datasets.pascal_voc07()\n",
+    "yolov3 = yolk.models.yolov3()\n",
+    "\n",
+    "yolov3.compile(\n",
+    "        loss=yolk.losses.yolov3Loss\n",
+    "        optimizer='adam', metrics=['coco']\n",
+    "    )\n",
+    "    \n",
+    "yolov3.fit_generator(\n",
+    "        generator=voc_train,\n",
+    "        validation_data=voc_valid,\n",
+    "        epochs=20\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

yolk/datasets/pascal.py

@@ -0,0 +1,133 @@
+
+def create_generators(args, preprocess_image):
+    """ Create generators for training and validation.
+
+    Args
+        args             : parseargs object containing configuration for generators.
+        preprocess_image : Function that preprocesses an image for the network.
+    """
+    common_args = {
+        'batch_size'       : args.batch_size,
+        'config'           : args.config,
+        'image_min_side'   : args.image_min_side,
+        'image_max_side'   : args.image_max_side,
+        'preprocess_image' : preprocess_image,
+    }
+
+    # create random transform generator for augmenting training data
+    if args.random_transform:
+        transform_generator = random_transform_generator(
+            min_rotation=-0.1,
+            max_rotation=0.1,
+            min_translation=(-0.1, -0.1),
+            max_translation=(0.1, 0.1),
+            min_shear=-0.1,
+            max_shear=0.1,
+            min_scaling=(0.9, 0.9),
+            max_scaling=(1.1, 1.1),
+            flip_x_chance=0.5,
+            flip_y_chance=0.5,
+        )
+        visual_effect_generator = random_visual_effect_generator(
+            contrast_range=(0.9, 1.1),
+            brightness_range=(-.1, .1),
+            hue_range=(-0.05, 0.05),
+            saturation_range=(0.95, 1.05)
+        )
+    else:
+        transform_generator = random_transform_generator(flip_x_chance=0.5)
+        visual_effect_generator = None
+
+    if args.dataset_type == 'coco':
+        # import here to prevent unnecessary dependency on cocoapi
+        from ..preprocessing.coco import CocoGenerator
+
+        train_generator = CocoGenerator(
+            args.coco_path,
+            'train2017',
+            transform_generator=transform_generator,
+            visual_effect_generator=visual_effect_generator,
+            **common_args
+        )
+
+        validation_generator = CocoGenerator(
+            args.coco_path,
+            'val2017',
+            shuffle_groups=False,
+            **common_args
+        )
+    elif args.dataset_type == 'pascal':
+        train_generator = PascalVocGenerator(
+            args.pascal_path,
+            'trainval',
+            transform_generator=transform_generator,
+            visual_effect_generator=visual_effect_generator,
+            **common_args
+        )
+
+        validation_generator = PascalVocGenerator(
+            args.pascal_path,
+            'test',
+            shuffle_groups=False,
+            **common_args
+        )
+    elif args.dataset_type == 'csv':
+        train_generator = CSVGenerator(
+            args.annotations,
+            args.classes,
+            transform_generator=transform_generator,
+            visual_effect_generator=visual_effect_generator,
+            **common_args
+        )
+
+        if args.val_annotations:
+            validation_generator = CSVGenerator(
+                args.val_annotations,
+                args.classes,
+                shuffle_groups=False,
+                **common_args
+            )
+        else:
+            validation_generator = None
+    elif args.dataset_type == 'oid':
+        train_generator = OpenImagesGenerator(
+            args.main_dir,
+            subset='train',
+            version=args.version,
+            labels_filter=args.labels_filter,
+            annotation_cache_dir=args.annotation_cache_dir,
+            parent_label=args.parent_label,
+            transform_generator=transform_generator,
+            visual_effect_generator=visual_effect_generator,
+            **common_args
+        )
+
+        validation_generator = OpenImagesGenerator(
+            args.main_dir,
+            subset='validation',
+            version=args.version,
+            labels_filter=args.labels_filter,
+            annotation_cache_dir=args.annotation_cache_dir,
+            parent_label=args.parent_label,
+            shuffle_groups=False,
+            **common_args
+        )
+    elif args.dataset_type == 'kitti':
+        train_generator = KittiGenerator(
+            args.kitti_path,
+            subset='train',
+            transform_generator=transform_generator,
+            visual_effect_generator=visual_effect_generator,
+            **common_args
+        )
+
+        validation_generator = KittiGenerator(
+            args.kitti_path,
+            subset='val',
+            shuffle_groups=False,
+            **common_args
+        )
+    else:
+        raise ValueError('Invalid data type received: {}'.format(args.dataset_type))
+
+    return train_generator, validation_generator