Created
November 21, 2022 07:14
-
-
Save daniel-falk/37d1ae23c2e4e458ecf4f63f35bcbbad to your computer and use it in GitHub Desktop.
deeplake-corruption-issues.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"provenance": [], | |
"authorship_tag": "ABX9TyNwc1N/XTlDsb267szwgT5D", | |
"include_colab_link": true | |
}, | |
"kernelspec": { | |
"name": "python3", | |
"display_name": "Python 3" | |
}, | |
"language_info": { | |
"name": "python" | |
} | |
}, | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "view-in-github", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"<a href=\"https://colab.research.google.com/gist/daniel-falk/37d1ae23c2e4e458ecf4f63f35bcbbad/deeplake-corruption-issues.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"id": "dXAaOeG6Fl-O" | |
}, | |
"outputs": [], | |
"source": [ | |
"!pip install deeplake==3.1.0" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"import deeplake\n", | |
"import numpy as np" | |
], | |
"metadata": { | |
"id": "4EcGwZ_eFv-r" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"ds = deeplake.empty(\"/tmp/ds1\", overwrite=True)\n", | |
"\n", | |
"ds.create_tensor(\"images\", htype=\"image\", sample_compression=\"jpeg\")\n", | |
"ds.create_tensor(\"labels\", htype=\"class_label\")\n", | |
"ds.create_tensor(\"description\", htype=\"text\")\n", | |
"\n", | |
"ds.commit(\"Empty\")\n", | |
"\n", | |
"s = np.ones(shape=(3,3,1))\n", | |
"\n", | |
"NUM_SAMPLES = 255\n", | |
"ds.extend({\n", | |
" \"images\": [(s.copy() * n).astype(np.uint8) for n in range(NUM_SAMPLES)],\n", | |
" \"labels\": [n for n in range(NUM_SAMPLES)],\n", | |
" \"description\": [f\"img{n}\" for n in range(NUM_SAMPLES)],\n", | |
"})\n", | |
"ds.commit(f\"Add img 1-{NUM_SAMPLES - 1} to main\")" | |
], | |
"metadata": { | |
"id": "DRgIUeqxF9ne" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"@deeplake.compute\n", | |
"def append_sum_value(sample_in, sample_out):\n", | |
" img = sample_in.images.numpy()\n", | |
" sample_out.img_sums.append(img.sum())\n", | |
"\n", | |
" sample_out.images.append(sample_in.images)\n", | |
" sample_out.labels.append(sample_in.labels)\n", | |
" sample_out.description.append(sample_in.description.text())\n", | |
"\n", | |
"ds2 = deeplake.load(\"/tmp/ds1\")\n", | |
"ds2.checkout(ds2.commits[-1][\"commit\"]) # Checkout the empty root\n", | |
"ds2.checkout(\"branch2\", create=True)\n", | |
"ds2.create_tensor(\"img_sums\", htype=\"generic\")\n", | |
"append_sum_value().eval(ds, ds2, num_workers=8)\n", | |
"ds2.commit(\"Added samples with image sums\")" | |
], | |
"metadata": { | |
"id": "HLOMBLExHsCn" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"import numpy as np\n", | |
"\n", | |
"idx_to_remove = np.where(ds2.img_sums.numpy() < ds2.img_sums.numpy().mean())[0]" | |
], | |
"metadata": { | |
"id": "RKYYO5ySICNA" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"for idx in sorted(map(int, idx_to_remove), reverse=True):\n", | |
" ds.pop(idx)\n", | |
"\n", | |
"ds.commit(\"Removed dark samples\")" | |
], | |
"metadata": { | |
"id": "gthtJA4DAwxR" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# In my script that looks like this but are a bit more complex,\n", | |
"# this line would fail when accessing the label\n", | |
"for sample in ds:\n", | |
" print(sample.images.numpy()[0,0,0], sample.labels.numpy()[0]) # Would sometimes get an exception" | |
], | |
"metadata": { | |
"id": "8BArGquQKBh0" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment