Open
Conversation
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
brmarkus
reviewed
Jan 20, 2026
Collaborator
|
hi @zhaohb Thanks for your contribution. Please help to address my feedback. |
openvino-dev-samples
approved these changes
Feb 9, 2026
|
|
||
| This notebook shows an end-to-end workflow for **PaddleOCR-VL-1.5 → OpenVINO**: | ||
|
|
||
| - Download the pretrained PaddleOCR-VL-1.5/PaddleOCR-VL model. |
Collaborator
There was a problem hiding this comment.
Is this notebook for both or only 1.5, if its for both, please add a model selector for 1.0.
| "\n", | ||
| "# Install the rest dependencies from PyPI (keep existing versions/constraints)\n", | ||
| "pip_install(\n", | ||
| " \"-U\",\n", |
Collaborator
There was a problem hiding this comment.
Suggested change
| " \"-U\",\n", | |
| " \"-q\",\n", | |
| " \"-U\",\n", |
Collaborator
There was a problem hiding this comment.
for silent installtion
| "output_type": "stream", | ||
| "name": "stdout", | ||
| "text": [ | ||
| "stateful model inputs: [<Output: names[attention_mask, 211] shape[?,?] type: f32>, <Output: names[position_ids, 237, 238] shape[?,?,?] type: i64>, <Output: names[24] shape[?,?,?,128] type: f32>, <Output: names[25] shape[?,?,?,128] type: f32>, <Output: names[26] shape[?,?,?,128] type: f32>, <Output: names[27] shape[?,?,?,128] type: f32>, <Output: names[28] shape[?,?,?,128] type: f32>, <Output: names[29] shape[?,?,?,128] type: f32>, <Output: names[30] shape[?,?,?,128] type: f32>, <Output: names[31] shape[?,?,?,128] type: f32>, <Output: names[32] shape[?,?,?,128] type: f32>, <Output: names[33] shape[?,?,?,128] type: f32>, <Output: names[34] shape[?,?,?,128] type: f32>, <Output: names[35] shape[?,?,?,128] type: f32>, <Output: names[36] shape[?,?,?,128] type: f32>, <Output: names[37] shape[?,?,?,128] type: f32>, <Output: names[38] shape[?,?,?,128] type: f32>, <Output: names[39] shape[?,?,?,128] type: f32>, <Output: names[40] shape[?,?,?,128] type: f32>, <Output: names[41] shape[?,?,?,128] type: f32>, <Output: names[42] shape[?,?,?,128] type: f32>, <Output: names[43] shape[?,?,?,128] type: f32>, <Output: names[44] shape[?,?,?,128] type: f32>, <Output: names[45] shape[?,?,?,128] type: f32>, <Output: names[46] shape[?,?,?,128] type: f32>, <Output: names[47] shape[?,?,?,128] type: f32>, <Output: names[48] shape[?,?,?,128] type: f32>, <Output: names[49] shape[?,?,?,128] type: f32>, <Output: names[50] shape[?,?,?,128] type: f32>, <Output: names[51] shape[?,?,?,128] type: f32>, <Output: names[52] shape[?,?,?,128] type: f32>, <Output: names[53] shape[?,?,?,128] type: f32>, <Output: names[54] shape[?,?,?,128] type: f32>, <Output: names[55] shape[?,?,?,128] type: f32>, <Output: names[56] shape[?,?,?,128] type: f32>, <Output: names[57] shape[?,?,?,128] type: f32>, <Output: names[58] shape[?,?,?,128] type: f32>, <Output: names[59] shape[?,?,?,128] type: f32>, <Output: names[273, inputs_embeds, 262, hidden_states.1] shape[?,?,?] type: f32>]\n", |
Collaborator
There was a problem hiding this comment.
Should we print out these layer information ?
| "core = ov.Core()\n", | ||
| "\n", | ||
| "paddleocr_vl_model = OVPaddleOCRVLForCausalLM(\n", | ||
| " core=core,\n", |
Collaborator
There was a problem hiding this comment.
What's the purpose of this param ? can we initialize the openvino inside of wrapper ?
| "✅ INT8 compressed model saved to c:\\hongbo\\paddle_ocr_vl\\openvino_notebooks\\notebooks\\paddleocr_vl\\ov_paddleocr_vl_model/llm_stateful_int8.xml\n", | ||
| "✅ PaddleOCR-VL model has been successfully converted to OpenVINO format.\n", | ||
| "✅ Conversion complete.\n", | ||
| "✅ Resources released.\n" |
Collaborator
There was a problem hiding this comment.
Can we skip the step of model conversion if ov model existing already ?
| "try:\n", | ||
| " demo.launch(debug=True)\n", | ||
| "except Exception:\n", | ||
| " demo.launch(debug=True, share=True)\n", |
Collaborator
There was a problem hiding this comment.
the size of text in example picture is too small for demonstration, could you improve it ?
| " d = ImageDraw.Draw(im)\n", | ||
| " d.text(\n", | ||
| " (40, 40),\n", | ||
| " \"PaddleOCR-VL OpenVINO test\\nOCR: Hello 123\\nTable: A | B | C\",\n", |
Collaborator
There was a problem hiding this comment.
I think its better to use a real picture for demonstration rather than a manually created one.
Meanwhile please also show the original picture along with the predictions.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.