Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 55 additions & 48 deletions examples/analysing-image-classification-dataset.ipynb
Original file line number Diff line number Diff line change
@@ -1,7 +1,6 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "SwSYWR4vzk_e",
"metadata": {
Expand Down Expand Up @@ -149,7 +148,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "8aba34e1",
"metadata": {},
Expand Down Expand Up @@ -247,8 +245,8 @@
"</div>"
],
"text/plain": [
" path noisy_labels_0 noisy_labels_1 \\\n",
"0 train/n02979186/n02979186_9036.JPEG n02979186 n02979186 \n",
" path noisy_labels_0 noisy_labels_1 \n",
"0 train/n02979186/n02979186_9036.JPEG n02979186 n02979186 \\\n",
"1 train/n02979186/n02979186_11957.JPEG n02979186 n02979186 \n",
"2 train/n02979186/n02979186_9715.JPEG n02979186 n02979186 \n",
"\n",
Expand All @@ -269,7 +267,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "dfc957bf",
"metadata": {},
Expand Down Expand Up @@ -322,41 +319,41 @@
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>img_filename</th>\n",
" <th>filename</th>\n",
" <th>label</th>\n",
" <th>split</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>train/n02979186/n02979186_9036.JPEG</td>\n",
" <td>imagenette2-160/train/n02979186/n02979186_9036...</td>\n",
" <td>cassette_player</td>\n",
" <td>train</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>train/n02979186/n02979186_11957.JPEG</td>\n",
" <td>imagenette2-160/train/n02979186/n02979186_1195...</td>\n",
" <td>cassette_player</td>\n",
" <td>train</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>train/n02979186/n02979186_9715.JPEG</td>\n",
" <td>imagenette2-160/train/n02979186/n02979186_9715...</td>\n",
" <td>cassette_player</td>\n",
" <td>train</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>train/n02979186/n02979186_21736.JPEG</td>\n",
" <td>imagenette2-160/train/n02979186/n02979186_2173...</td>\n",
" <td>cassette_player</td>\n",
" <td>train</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>train/n02979186/ILSVRC2012_val_00046953.JPEG</td>\n",
" <td>imagenette2-160/train/n02979186/ILSVRC2012_val...</td>\n",
" <td>cassette_player</td>\n",
" <td>train</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
Expand All @@ -366,52 +363,65 @@
" </tr>\n",
" <tr>\n",
" <th>13389</th>\n",
" <td>val/n03425413/n03425413_17521.JPEG</td>\n",
" <td>imagenette2-160/val/n03425413/n03425413_17521....</td>\n",
" <td>gas_pump</td>\n",
" <td>val</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13390</th>\n",
" <td>val/n03425413/n03425413_20711.JPEG</td>\n",
" <td>imagenette2-160/val/n03425413/n03425413_20711....</td>\n",
" <td>gas_pump</td>\n",
" <td>val</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13391</th>\n",
" <td>val/n03425413/n03425413_19050.JPEG</td>\n",
" <td>imagenette2-160/val/n03425413/n03425413_19050....</td>\n",
" <td>gas_pump</td>\n",
" <td>val</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13392</th>\n",
" <td>val/n03425413/n03425413_13831.JPEG</td>\n",
" <td>imagenette2-160/val/n03425413/n03425413_13831....</td>\n",
" <td>gas_pump</td>\n",
" <td>val</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13393</th>\n",
" <td>val/n03425413/n03425413_1242.JPEG</td>\n",
" <td>imagenette2-160/val/n03425413/n03425413_1242.JPEG</td>\n",
" <td>gas_pump</td>\n",
" <td>val</td>\n",
" <td>imagenette2-160</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>13394 rows × 3 columns</p>\n",
"</div>"
],
"text/plain": [
" img_filename label split\n",
"0 train/n02979186/n02979186_9036.JPEG cassette_player train\n",
"1 train/n02979186/n02979186_11957.JPEG cassette_player train\n",
"2 train/n02979186/n02979186_9715.JPEG cassette_player train\n",
"3 train/n02979186/n02979186_21736.JPEG cassette_player train\n",
"4 train/n02979186/ILSVRC2012_val_00046953.JPEG cassette_player train\n",
"... ... ... ...\n",
"13389 val/n03425413/n03425413_17521.JPEG gas_pump val\n",
"13390 val/n03425413/n03425413_20711.JPEG gas_pump val\n",
"13391 val/n03425413/n03425413_19050.JPEG gas_pump val\n",
"13392 val/n03425413/n03425413_13831.JPEG gas_pump val\n",
"13393 val/n03425413/n03425413_1242.JPEG gas_pump val\n",
" filename label \n",
"0 imagenette2-160/train/n02979186/n02979186_9036... cassette_player \\\n",
"1 imagenette2-160/train/n02979186/n02979186_1195... cassette_player \n",
"2 imagenette2-160/train/n02979186/n02979186_9715... cassette_player \n",
"3 imagenette2-160/train/n02979186/n02979186_2173... cassette_player \n",
"4 imagenette2-160/train/n02979186/ILSVRC2012_val... cassette_player \n",
"... ... ... \n",
"13389 imagenette2-160/val/n03425413/n03425413_17521.... gas_pump \n",
"13390 imagenette2-160/val/n03425413/n03425413_20711.... gas_pump \n",
"13391 imagenette2-160/val/n03425413/n03425413_19050.... gas_pump \n",
"13392 imagenette2-160/val/n03425413/n03425413_13831.... gas_pump \n",
"13393 imagenette2-160/val/n03425413/n03425413_1242.JPEG gas_pump \n",
"\n",
" split \n",
"0 imagenette2-160 \n",
"1 imagenette2-160 \n",
"2 imagenette2-160 \n",
"3 imagenette2-160 \n",
"4 imagenette2-160 \n",
"... ... \n",
"13389 imagenette2-160 \n",
"13390 imagenette2-160 \n",
"13391 imagenette2-160 \n",
"13392 imagenette2-160 \n",
"13393 imagenette2-160 \n",
"\n",
"[13394 rows x 3 columns]"
]
Expand All @@ -428,6 +438,9 @@
"# rename columns to fastdup's column names\n",
"df_annot = df_annot.rename({'noisy_labels_0': 'label', 'path': 'filename'}, axis='columns')\n",
"\n",
"# append datadir\n",
"df_annot['filename'] = df_annot['filename'].apply(lambda x: data_dir + x)\n",
"\n",
"# create split column\n",
"df_annot['split'] = df_annot['filename'].apply(lambda x: x.split(\"/\")[0])\n",
"\n",
Expand All @@ -439,7 +452,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "0c648ed1-5016-4230-9873-546eb510b764",
"metadata": {
Expand All @@ -453,17 +465,17 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 6,
"id": "7f69d8b2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'0.918'"
"'0.922'"
]
},
"execution_count": 1,
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
Expand Down Expand Up @@ -522,7 +534,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "62e35a12-fadd-4b3f-bcab-69e6e67862a4",
"metadata": {},
Expand Down Expand Up @@ -1662,7 +1673,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "67378b58",
"metadata": {},
Expand Down Expand Up @@ -3998,7 +4008,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "c2c393be-2b42-4814-8688-03d2be9e8998",
"metadata": {},
Expand Down Expand Up @@ -4833,7 +4842,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "e10989e1",
"metadata": {},
Expand Down Expand Up @@ -7707,7 +7715,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "569cb878",
"metadata": {},
Expand Down Expand Up @@ -7778,7 +7785,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.10.11"
}
},
"nbformat": 4,
Expand Down
Loading