{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#default_exp vision.data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"from local.test import *\n",
"from local.torch_basics import *\n",
"from local.data.all import *\n",
"\n",
"from local.vision.core import *"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from local.notebook.showdoc import *"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Vision data\n",
"\n",
"> Helper functions to get data in a `DataBunch` un the vision applicaiton and higher class `ImageDataBunch`"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ImageDataBunch -"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"class ImageDataBunch(DataBunch): \n",
" \n",
" @classmethod\n",
" @delegates(DataBunch.from_dblock)\n",
" def from_folder(cls, path, train='train', valid='valid', valid_pct=None, seed=None, vocab=None, **kwargs):\n",
" \"Create from imagenet style dataset in `path` with `train`,`valid`,`test` subfolders (or provide `valid_pct`).\"\n",
" splitter = GrandparentSplitter(train_name=train, valid_name=valid) if valid_pct is None else RandomSplitter(valid_pct, seed=seed)\n",
" dblock = DataBlock(blocks=(ImageBlock, CategoryBlock(vocab=vocab)),\n",
" get_items=get_image_files,\n",
" splitter=splitter,\n",
" get_y=parent_label)\n",
" return cls.from_dblock(dblock, path, path=path, **kwargs)\n",
"\n",
" @classmethod\n",
" @delegates(DataBunch.from_dblock)\n",
" def from_name_func(cls, path, fnames, label_func, valid_pct=0.2, seed=None, **kwargs):\n",
" \"Create from list of `fnames` in `path`s with `label_func`.\"\n",
" dblock = DataBlock(blocks=(ImageBlock, CategoryBlock),\n",
" splitter=RandomSplitter(valid_pct, seed=seed),\n",
" get_y=label_func)\n",
" return cls.from_dblock(dblock, fnames, path=path, **kwargs)\n",
" \n",
" @classmethod\n",
" @delegates(DataBunch.from_dblock)\n",
" def from_name_re(cls, path, fnames, pat, **kwargs):\n",
" \"Create from list of `fnames` in `path`s with re expression `pat`.\"\n",
" return cls.from_name_func(path, fnames, RegexLabeller(pat), **kwargs)\n",
" \n",
" @classmethod\n",
" @delegates(DataBunch.from_dblock)\n",
" def from_df(cls, df, path='.', valid_pct=0.2, seed=None, fn_col=0, folder=None, suff='', label_col=1, label_delim=None, y_block=None, **kwargs):\n",
" pref = f'{Path(path) if folder is None else Path(path)/folder}{os.path.sep}'\n",
" if y_block is None: y_block = MultiCategoryBlock if is_listy(label_col) and len(label_col) > 1 else CategoryBlock\n",
" dblock = DataBlock(blocks=(ImageBlock, y_block),\n",
" get_x=ColReader(fn_col, pref=pref, suff=suff),\n",
" get_y=ColReader(label_col, label_delim=label_delim),\n",
" splitter=RandomSplitter(valid_pct, seed=seed))\n",
" return cls.from_dblock(dblock, df, path=path, **kwargs)\n",
" \n",
" @classmethod\n",
" def from_csv(cls, path, csv_fname='labels.csv', header='infer', delimiter=None, **kwargs):\n",
" df = pd.read_csv(Path(path)/csv_fname, header=header, delimiter=delimiter)\n",
" return cls.from_df(df, path=path, **kwargs)\n",
" \n",
" @classmethod\n",
" @delegates(DataBunch.from_dblock)\n",
" def from_lists(cls, path, fnames, labels, valid_pct=0.2, seed:int=None, y_block=None, **kwargs):\n",
" \"Create from list of `fnames` in `path`.\"\n",
" if y_block is None:\n",
" y_block = MultiCategoryBlock if is_listy(labels[0]) and len(labels[0]) > 1 else (TransformBlock if isinstance(labels[0], float) else CategoryBlock)\n",
" dblock = DataBlock(blocks=(ImageBlock, y_block),\n",
" splitter=RandomSplitter(valid_pct, seed=seed))\n",
" return cls.from_dblock(dblock, (fnames, labels), path=path, **kwargs)\n",
" \n",
"ImageDataBunch.from_csv = delegates(to=ImageDataBunch.from_df)(ImageDataBunch.from_csv)\n",
"ImageDataBunch.from_name_re = delegates(to=ImageDataBunch.from_name_func)(ImageDataBunch.from_name_re)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"\n",
"\n",
"> ImageDataBunch.from_folder(**`path`**, **`train`**=*`'train'`*, **`valid`**=*`'valid'`*, **`valid_pct`**=*`None`*, **`seed`**=*`None`*, **`vocab`**=*`None`*, **`type_tfms`**=*`None`*, **`item_tfms`**=*`None`*, **`batch_tfms`**=*`None`*, **`bs`**=*`16`*, **`shuffle`**=*`False`*, **`num_workers`**=*`None`*, **`pin_memory`**=*`False`*, **`timeout`**=*`0`*, **`drop_last`**=*`False`*, **`indexed`**=*`None`*, **`n`**=*`None`*, **`wif`**=*`None`*, **`before_iter`**=*`None`*, **`create_batches`**=*`None`*, **`create_item`**=*`None`*, **`after_item`**=*`None`*, **`before_batch`**=*`None`*, **`create_batch`**=*`None`*, **`retain`**=*`None`*, **`after_batch`**=*`None`*, **`after_iter`**=*`None`*)\n",
"\n",
"Create from imagenet style dataset in `path` with `train`,`valid`,[`test`](/test.html) subfolders (or provide `valid_pct`)."
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_doc(ImageDataBunch.from_folder)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"\n",
"\n",
"> ImageDataBunch.from_name_func(**`path`**, **`fnames`**, **`label_func`**, **`valid_pct`**=*`0.2`*, **`seed`**=*`None`*, **`type_tfms`**=*`None`*, **`item_tfms`**=*`None`*, **`batch_tfms`**=*`None`*, **`bs`**=*`16`*, **`shuffle`**=*`False`*, **`num_workers`**=*`None`*, **`pin_memory`**=*`False`*, **`timeout`**=*`0`*, **`drop_last`**=*`False`*, **`indexed`**=*`None`*, **`n`**=*`None`*, **`wif`**=*`None`*, **`before_iter`**=*`None`*, **`create_batches`**=*`None`*, **`create_item`**=*`None`*, **`after_item`**=*`None`*, **`before_batch`**=*`None`*, **`create_batch`**=*`None`*, **`retain`**=*`None`*, **`after_batch`**=*`None`*, **`after_iter`**=*`None`*)\n",
"\n",
"Create from list of `fnames` in `path`s with `label_func`."
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_doc(ImageDataBunch.from_name_func)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"\n",
"\n",
"> ImageDataBunch.from_name_re(**`path`**, **`fnames`**, **`pat`**, **`valid_pct`**=*`0.2`*, **`seed`**=*`None`*, **`type_tfms`**=*`None`*, **`item_tfms`**=*`None`*, **`batch_tfms`**=*`None`*, **`bs`**=*`16`*, **`shuffle`**=*`False`*, **`num_workers`**=*`None`*, **`pin_memory`**=*`False`*, **`timeout`**=*`0`*, **`drop_last`**=*`False`*, **`indexed`**=*`None`*, **`n`**=*`None`*, **`wif`**=*`None`*, **`before_iter`**=*`None`*, **`create_batches`**=*`None`*, **`create_item`**=*`None`*, **`after_item`**=*`None`*, **`before_batch`**=*`None`*, **`create_batch`**=*`None`*, **`retain`**=*`None`*, **`after_batch`**=*`None`*, **`after_iter`**=*`None`*)\n",
"\n",
"Create from list of `fnames` in `path`s with re expression `pat`."
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_doc(ImageDataBunch.from_name_re)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"\n",
"\n",
"> ImageDataBunch.from_df(**`df`**, **`path`**=*`'.'`*, **`valid_pct`**=*`0.2`*, **`seed`**=*`None`*, **`fn_col`**=*`0`*, **`pref`**=*`''`*, **`suff`**=*`''`*, **`label_col`**=*`1`*, **`label_delim`**=*`None`*, **`type_tfms`**=*`None`*, **`item_tfms`**=*`None`*, **`batch_tfms`**=*`None`*, **`bs`**=*`16`*, **`shuffle`**=*`False`*, **`num_workers`**=*`None`*, **`pin_memory`**=*`False`*, **`timeout`**=*`0`*, **`drop_last`**=*`False`*, **`indexed`**=*`None`*, **`n`**=*`None`*, **`wif`**=*`None`*, **`before_iter`**=*`None`*, **`create_batches`**=*`None`*, **`create_item`**=*`None`*, **`after_item`**=*`None`*, **`before_batch`**=*`None`*, **`create_batch`**=*`None`*, **`retain`**=*`None`*, **`after_batch`**=*`None`*, **`after_iter`**=*`None`*)\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_doc(ImageDataBunch.from_df)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"\n",
"\n",
"> ImageDataBunch.from_csv(**`path`**, **`csv_fname`**=*`'labels.csv'`*, **`header`**=*`'infer'`*, **`delimiter`**=*`None`*, **`valid_pct`**=*`0.2`*, **`seed`**=*`None`*, **`fn_col`**=*`0`*, **`pref`**=*`''`*, **`suff`**=*`''`*, **`label_col`**=*`1`*, **`label_delim`**=*`None`*, **`type_tfms`**=*`None`*, **`item_tfms`**=*`None`*, **`batch_tfms`**=*`None`*, **`bs`**=*`16`*, **`shuffle`**=*`False`*, **`num_workers`**=*`None`*, **`pin_memory`**=*`False`*, **`timeout`**=*`0`*, **`drop_last`**=*`False`*, **`indexed`**=*`None`*, **`n`**=*`None`*, **`wif`**=*`None`*, **`before_iter`**=*`None`*, **`create_batches`**=*`None`*, **`create_item`**=*`None`*, **`after_item`**=*`None`*, **`before_batch`**=*`None`*, **`create_batch`**=*`None`*, **`retain`**=*`None`*, **`after_batch`**=*`None`*, **`after_iter`**=*`None`*)\n",
"\n"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_doc(ImageDataBunch.from_csv)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"\n",
"\n",
"> ImageDataBunch.from_lists(**`path`**, **`fnames`**, **`labels`**, **`valid_pct`**=*`0.2`*, **`seed`**:`int`=*`None`*, **`y_block`**=*`None`*, **`type_tfms`**=*`None`*, **`item_tfms`**=*`None`*, **`batch_tfms`**=*`None`*, **`bs`**=*`16`*, **`shuffle`**=*`False`*, **`num_workers`**=*`None`*, **`pin_memory`**=*`False`*, **`timeout`**=*`0`*, **`drop_last`**=*`False`*, **`indexed`**=*`None`*, **`n`**=*`None`*, **`wif`**=*`None`*, **`before_iter`**=*`None`*, **`create_batches`**=*`None`*, **`create_item`**=*`None`*, **`after_item`**=*`None`*, **`before_batch`**=*`None`*, **`create_batch`**=*`None`*, **`retain`**=*`None`*, **`after_batch`**=*`None`*, **`after_iter`**=*`None`*)\n",
"\n",
"Create from list of `fnames` in `path`."
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_doc(ImageDataBunch.from_lists)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Show methods"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"def get_grid(n, rows=None, cols=None, add_vert=0, figsize=None, double=False, title=None, return_fig=False):\n",
" rows = rows or int(np.ceil(math.sqrt(n)))\n",
" cols = cols or int(np.ceil(n/rows))\n",
" if double: cols*=2 ; n*=2\n",
" figsize = (cols*3, rows*3+add_vert) if figsize is None else figsize\n",
" fig,axs = subplots(rows, cols, figsize=figsize)\n",
" axs = axs.flatten()\n",
" for ax in axs[n:]: ax.set_axis_off()\n",
" if title is not None: fig.suptitle(title, weight='bold', size=14)\n",
" return (fig,axs) if return_fig else axs"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"@typedispatch\n",
"def show_batch(x:TensorImage, y, samples, ctxs=None, max_n=10, rows=None, cols=None, figsize=None, **kwargs):\n",
" if ctxs is None: ctxs = get_grid(min(len(samples), max_n), rows=rows, cols=cols, figsize=figsize)\n",
" ctxs = show_batch[object](x, y, samples, ctxs=ctxs, max_n=max_n, **kwargs)\n",
" return ctxs"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Helper functions for object detection"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# export\n",
"def clip_remove_empty(bbox, label):\n",
" \"Clip bounding boxes with image border and label background the empty ones.\"\n",
" bbox = torch.clamp(bbox, -1, 1)\n",
" empty = ((bbox[...,2] - bbox[...,0])*(bbox[...,3] - bbox[...,1]) < 0.)\n",
" return (bbox[~empty], label[~empty])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"bb = tensor([[-2,-0.5,0.5,1.5], [-0.5,-0.5,0.5,0.5], [1,0.5,0.5,0.75], [-0.5,-0.5,0.5,0.5]])\n",
"bb,lbl = clip_remove_empty(bb, tensor([1,2,3,2]))\n",
"test_eq(bb, tensor([[-1,-0.5,0.5,1.], [-0.5,-0.5,0.5,0.5], [-0.5,-0.5,0.5,0.5]]))\n",
"test_eq(lbl, tensor([1,2,2]))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"def bb_pad(samples, pad_idx=0):\n",
" \"Function that collect `samples` of labelled bboxes and adds padding with `pad_idx`.\"\n",
" samples = [(s[0], *clip_remove_empty(*s[1:])) for s in samples]\n",
" max_len = max([len(s[2]) for s in samples])\n",
" def _f(img,bbox,lbl):\n",
" bbox = torch.cat([bbox,bbox.new_zeros(max_len-bbox.shape[0], 4)])\n",
" lbl = torch.cat([lbl, lbl .new_zeros(max_len-lbl .shape[0])+pad_idx])\n",
" return img,bbox,lbl\n",
" return [_f(*s) for s in samples]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"img1,img2 = TensorImage(torch.randn(16,16,3)),TensorImage(torch.randn(16,16,3))\n",
"bb1 = tensor([[-2,-0.5,0.5,1.5], [-0.5,-0.5,0.5,0.5], [1,0.5,0.5,0.75], [-0.5,-0.5,0.5,0.5]])\n",
"lbl1 = tensor([1, 2, 3, 2])\n",
"bb2 = tensor([[-0.5,-0.5,0.5,0.5], [-0.5,-0.5,0.5,0.5]])\n",
"lbl2 = tensor([2, 2])\n",
"samples = [(img1, bb1, lbl1), (img2, bb2, lbl2)]\n",
"res = bb_pad(samples)\n",
"non_empty = tensor([True,True,False,True])\n",
"test_eq(res[0][0], img1)\n",
"test_eq(res[0][1], tensor([[-1,-0.5,0.5,1.], [-0.5,-0.5,0.5,0.5], [-0.5,-0.5,0.5,0.5]]))\n",
"test_eq(res[0][2], tensor([1,2,2]))\n",
"test_eq(res[1][0], img2)\n",
"test_eq(res[1][1], tensor([[-0.5,-0.5,0.5,0.5], [-0.5,-0.5,0.5,0.5], [0,0,0,0]]))\n",
"test_eq(res[1][2], tensor([2,2,0])) "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## `TransformBlock`s for vision"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"def ImageBlock(cls=PILImage): return TransformBlock(type_tfms=cls.create, batch_tfms=IntToFloatTensor)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"MaskBlock = TransformBlock(type_tfms=PILMask.create, batch_tfms=IntToFloatTensor)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"PointBlock = TransformBlock(type_tfms=TensorPoint.create, item_tfms=PointScaler)\n",
"BBoxBlock = TransformBlock(type_tfms=TensorBBox.create, item_tfms=PointScaler, dbunch_kwargs = {'before_batch': bb_pad})"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"BBoxBlock = TransformBlock(type_tfms=TensorBBox.create, item_tfms=PointScaler, dbunch_kwargs = {'before_batch': bb_pad})"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#export\n",
"def BBoxLblBlock(vocab=None, add_na=True):\n",
" return TransformBlock(type_tfms=MultiCategorize(vocab=vocab, add_na=add_na), item_tfms=BBoxLabeler)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Export -"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Converted 00_test.ipynb.\n",
"Converted 01_core_foundation.ipynb.\n",
"Converted 01a_core_utils.ipynb.\n",
"Converted 01b_core_dispatch.ipynb.\n",
"Converted 01c_core_transform.ipynb.\n",
"Converted 02_core_script.ipynb.\n",
"Converted 03_torchcore.ipynb.\n",
"Converted 03a_layers.ipynb.\n",
"Converted 04_data_load.ipynb.\n",
"Converted 05_data_core.ipynb.\n",
"Converted 06_data_transforms.ipynb.\n",
"Converted 07_data_block.ipynb.\n",
"Converted 08_vision_core.ipynb.\n",
"Converted 09_vision_augment.ipynb.\n",
"Converted 09a_vision_data.ipynb.\n",
"Converted 10_pets_tutorial.ipynb.\n",
"Converted 11_vision_models_xresnet.ipynb.\n",
"Converted 12_optimizer.ipynb.\n",
"Converted 13_learner.ipynb.\n",
"Converted 13a_metrics.ipynb.\n",
"Converted 14_callback_schedule.ipynb.\n",
"Converted 14a_callback_data.ipynb.\n",
"Converted 15_callback_hook.ipynb.\n",
"Converted 15a_vision_models_unet.ipynb.\n",
"Converted 16_callback_progress.ipynb.\n",
"Converted 17_callback_tracker.ipynb.\n",
"Converted 18_callback_fp16.ipynb.\n",
"Converted 19_callback_mixup.ipynb.\n",
"Converted 20_interpret.ipynb.\n",
"Converted 20a_distributed.ipynb.\n",
"Converted 21_vision_learner.ipynb.\n",
"Converted 22_tutorial_imagenette.ipynb.\n",
"Converted 23_tutorial_transfer_learning.ipynb.\n",
"Converted 30_text_core.ipynb.\n",
"Converted 31_text_data.ipynb.\n",
"Converted 32_text_models_awdlstm.ipynb.\n",
"Converted 33_text_models_core.ipynb.\n",
"Converted 34_callback_rnn.ipynb.\n",
"Converted 35_tutorial_wikitext.ipynb.\n",
"Converted 36_text_models_qrnn.ipynb.\n",
"Converted 37_text_learner.ipynb.\n",
"Converted 38_tutorial_ulmfit.ipynb.\n",
"Converted 40_tabular_core.ipynb.\n",
"Converted 41_tabular_model.ipynb.\n",
"Converted 42_tabular_rapids.ipynb.\n",
"Converted 50_data_block_examples.ipynb.\n",
"Converted 60_medical_imaging.ipynb.\n",
"Converted 65_medical_text.ipynb.\n",
"Converted 70_callback_wandb.ipynb.\n",
"Converted 71_callback_tensorboard.ipynb.\n",
"Converted 90_notebook_core.ipynb.\n",
"Converted 91_notebook_export.ipynb.\n",
"Converted 92_notebook_showdoc.ipynb.\n",
"Converted 93_notebook_export2html.ipynb.\n",
"Converted 94_notebook_test.ipynb.\n",
"Converted 95_index.ipynb.\n",
"Converted 96_data_external.ipynb.\n",
"Converted 97_utils_test.ipynb.\n",
"Converted notebook2jekyll.ipynb.\n",
"Converted xse_resnext.ipynb.\n"
]
}
],
"source": [
"#hide\n",
"from local.notebook.export import notebook2script\n",
"notebook2script(all_fs=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}