Skip to content

Fix issue with decoder example notebook #447

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rrawther merged 6 commits into from
Jan 28, 2026
Merged

Fix issue with decoder example notebook #447

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
48cb995
Fix issue with decoder example notebook
SundarRajan28 Jan 20, 2026
3d616b6
Merge branch 'develop' into decoder_notebook_fix
LakshmiKumar23 Jan 20, 2026
2f36ce4
Merge branch 'develop' into decoder_notebook_fix
LakshmiKumar23 Jan 21, 2026
8ff90ad
Merge branch 'develop' into decoder_notebook_fix
LakshmiKumar23 Jan 26, 2026
1c15434
Remove device parameter from show_images function
SundarRajan28 Jan 26, 2026
7552720
Remove hardcoded path
SundarRajan28 Jan 28, 2026
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
20 changes: 9 additions & 11 deletions docs/examples/notebooks/decoder_examples.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from amd.rocal.pipeline import pipeline_def\n",
"from amd.rocal.plugin.generic import ROCALClassificationIterator\n",
"import amd.rocal.fn as fn\n",
Expand All @@ -37,11 +38,11 @@
"%matplotlib inline\n",
"\n",
"seed = 1549361629\n",
"image_dir = \"../../../data/images/AMD-tinyDataSet/\"\n",
"image_dir = f\"{os.environ.get('ROCM_PATH', '/opt/rocm')}/share/rocal/test/data/images/AMD-tinyDataSet/\"\n",
"batch_size = 4\n",
"gpu_id = 0\n",
"\n",
"def show_images(image_batch, device):\n",
"def show_images(image_batch):\n",
" columns = 4\n",
" rows = (batch_size + 1) // (columns)\n",
" fig = plt.figure(figsize = (32,(32 // columns) * rows))\n",
Expand All @@ -50,17 +51,14 @@
" plt.subplot(gs[j])\n",
" img = image_batch[j]\n",
" plt.axis(\"off\")\n",
" if device == \"cpu\":\n",
" plt.imshow(img)\n",
" else:\n",
" plt.imshow(cp.asnumpy(img))\n",
" plt.imshow(img)\n",
"\n",
"\n",
"def show_pipeline_output(pipe, device, device_id=0):\n",
" pipe.build()\n",
" data_loader = ROCALClassificationIterator(pipe, device, device_id)\n",
" images = next(iter(data_loader))\n",
" show_images(images[0][0], device)\n"
" show_images(images[0][0])\n"
]
},
{
Expand All @@ -70,7 +68,7 @@
"source": [
"## Image Decoder (CPU)\n",
"\n",
"`decoders.image` decodes images stored in common formats (including JPEG, JPEG2000, TIFF, PNG)"
"`decoders.image` decodes images stored in JPEG format"
]
},
{
Expand Down Expand Up @@ -130,7 +128,7 @@
"\n",
"`decoders.image` with GPU backend uses rocJpeg to offload the JPEG decoding process to the GPU’s built-in hardware decoder, if supported\n",
"\n",
"Note, that we repeat the examples shown above, changing only the device parameter. Both the operator and its other parameters stay the same and offer the same functionality - but now we use GPU acceleration.\n"
"Note, that we repeat the examples shown above, changing only the device and rocal_cpu parameters. Both the operator and its other parameters stay the same and offer the same functionality - but now we use GPU acceleration.\n"
]
},
{
Expand All @@ -139,7 +137,7 @@
"metadata": {},
"outputs": [],
"source": [
"pipe = image_decoder_pipeline(batch_size=batch_size, num_threads=1, device_id=gpu_id, rocal_cpu=True, tensor_layout=types.NHWC, \n",
"pipe = image_decoder_pipeline(batch_size=batch_size, num_threads=1, device_id=gpu_id, rocal_cpu=False, tensor_layout=types.NHWC, \n",
" reverse_channels=True, mean=[0,0,0], std = [255,255,255], device=\"gpu\")\n",
"show_pipeline_output(pipe, device=\"gpu\")"
]
Expand All @@ -162,7 +160,7 @@
"metadata": {},
"outputs": [],
"source": [
"pipe = image_decoder_random_crop_pipeline(batch_size=batch_size, num_threads=1, device_id=gpu_id, rocal_cpu=True, tensor_layout=types.NHWC, reverse_channels=True, \n",
"pipe = image_decoder_random_crop_pipeline(batch_size=batch_size, num_threads=1, device_id=gpu_id, rocal_cpu=False, tensor_layout=types.NHWC, reverse_channels=True, \n",
" mean=[0,0,0], std = [255,255,255], device=\"gpu\")\n",
"show_pipeline_output(pipe, device=\"gpu\")"
]
Expand Down