Merge main

.binder/apt.txt

@@ -1,4 +1,3 @@
-libpython3.7-dev
 ffmpeg
 libsm6
 libxext6

.ci/check_links.py

@@ -9,6 +9,15 @@
 
 NOTEBOOKS_ROOT = Path(__file__).resolve().parents[1]
 
+EXCEPTIONS_URLs = [
+    "medium.com", 
+    "https://www.paddlepaddle.org.cn/", 
+    "mybinder.org", 
+    "https://arxiv.org", 
+    "http://host.robots.ox.ac.uk", 
+    "https://gitee.com/"
+]
+
 def get_all_ast_nodes(ast_nodes):
     for node in ast_nodes:
         yield node
@@ -26,6 +35,18 @@ def get_all_references_from_md(md_path):
             yield node['link']
 
 
+def validate_colab_url(url: str) -> bool:
+    OPENVINO_COLAB_URL_PREFIX = 'https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/'
+
+    if not url.startswith(OPENVINO_COLAB_URL_PREFIX):
+        return
+
+    notebook_path = url.split(OPENVINO_COLAB_URL_PREFIX)[1]
+    absolute_notebook_path = NOTEBOOKS_ROOT / notebook_path
+
+    if not absolute_notebook_path.exists():
+        raise ValueError(f'notebook not found for colab url {url!r}')
+
 def main():
     all_passed = True
 
@@ -54,11 +75,22 @@ def complain(message):
                 continue
 
             try:
-                get = requests.get(url, timeout=5)
+                validate_colab_url(url)
+            except ValueError as err:
+                complain(f'{md_path}: {err}')
+
+            try:
+                get = requests.get(url, timeout=10)
                 if get.status_code != 200:
+                    if get.status_code in [500, 429, 443] and any([known_url in url for known_url in EXCEPTIONS_URLs]):
+                        print(f'SKIP - {md_path}: URL can not be reached {url!r}, status code {get.status_code}')
+                        continue
                     complain(f'{md_path}: URL can not be reached {url!r}, status code {get.status_code}')    
             except Exception as err:
-                complain(f'{md_path}: URL can not be reached {url!r}, error {err}')
+                if any([known_url in url for known_url in EXCEPTIONS_URLs]):
+                    print(f'SKIP - {md_path}: URL can not be reached {url!r}, error {err}')
+                else:    
+                    complain(f'{md_path}: URL can not be reached {url!r}, error {err}')
 
     sys.exit(0 if all_passed else 1)
 

.ci/convert_notebooks.py

@@ -3,13 +3,26 @@
 import subprocess # nosec - disable B404:import-subprocess check
 import time
 from pathlib import Path
+import nbformat
 
 
+def disable_gradio_debug(notebook_path):
+    nb = nbformat.read(notebook_path, as_version=nbformat.NO_CONVERT)
+    found = False
+    for cell in nb["cells"]:
+        if "gradio" in cell["source"] and "debug" in cell["source"]:
+            found = True
+            cell["source"] = cell["source"].replace("debug=True", "debug=False")
+
+    if found:
+        print(f"Disabled gradio debug mode for {notebook_path}")
+        nbformat.write(nb, str(notebook_path), version=nbformat.NO_CONVERT)
+
 def arguments():
     parser = argparse.ArgumentParser()
     parser.add_argument("--exclude_execution_file")
     parser.add_argument("--exclude_conversion_file")
-    parser.add_argument("--timeout", type=float, default=3600,
+    parser.add_argument("--timeout", type=float, default=7200,
                         help="timeout for notebook execution")
     parser.add_argument("--rst_dir", type=Path,
                         help="rst files output directory", default=Path("rst"))
@@ -40,12 +53,17 @@ def main():
         notebook_path = notebook.relative_to(root)
         if str(notebook_path) in ignore_conversion_list:
             continue
+        disable_gradio_debug(notebook_path)
         notebook_executed = notebook_path.parent / notebook_path.name.replace(".ipynb", "-with-output.ipynb")
         start = time.perf_counter()
         print(f"Convert {notebook_path}")
         if str(notebook_path) not in ignore_execution_list:
-            retcode = subprocess.run(["jupyter", "nbconvert",  "--log-level=INFO", "--execute", "--to",  "notebook", "--output",
-                                     str(notebook_executed),  '--output-dir', str(root), '--ExecutePreprocessor.kernel_name=python3', str(notebook_path)], timeout=args.timeout).returncode
+            try:
+                retcode = subprocess.run(["jupyter", "nbconvert",  "--log-level=INFO", "--execute", "--to",  "notebook", "--output",
+                                        str(notebook_executed),  '--output-dir', str(root), '--ExecutePreprocessor.kernel_name=python3', str(notebook_path)], timeout=args.timeout).returncode
+            except subprocess.TimeoutExpired:
+                retcode = -42
+                print(f"TIMEOUT: {notebook_path}")
             if retcode:
                 failed_notebooks.append(str(notebook_path))
                 continue
@@ -61,7 +79,7 @@ def main():
         print(f"Notebook conversion took: {end:.4f} s")
         if rst_retcode:
             rst_failed.append(str(notebook_path))
-    
+
     if failed_notebooks:
         print("EXECUTION FAILED:")
         print("\n".join(failed_notebooks))

.ci/convert_notebooks.sh

@@ -5,12 +5,14 @@ ignore_list=$*
 rstdir=$PWD"/rst_files"
 binderlist=$rstdir"/notebooks_with_binder_buttons.txt"
 colablist=$rstdir"/notebooks_with_colab_buttons.txt"
+notebooklist=$rstdir"/all_notebooks_paths.txt"
 tagslist=$rstdir"/notebooks_tags.json"
 mkdir -p $rstdir
 
 # List all notebooks that contain binder or colab buttons based on readme
 cat README.md | grep -oP "https://mybinder.org/v2.*?[0-9]{3}.*?ipynb" | sed 's#%2F#/#g' | xargs basename -a -s .ipynb | sort | uniq > $binderlist
 cat README.md | grep -oP "https://colab.research.google.com/github.*?[0-9]{3}.*?ipynb" | xargs basename -s .ipynb | sort | uniq > $colablist
+find notebooks -maxdepth 2 -name "*.ipynb" | sort > $notebooklist
 taggerpath=$(git ls-files "*tagger.py")
 notebookspath=$(git ls-files "*.ipynb"| head -n 1)
 keywordspath=$(git ls-files "*keywords.json")

.ci/ignore_convert_execution.txt

@@ -1,25 +1,65 @@
 notebooks/107-speech-recognition-quantization/107-speech-recognition-quantization-data2vec.ipynb
 notebooks/108-gpu-device/108-gpu-device.ipynb
 notebooks/117-model-server/117-model-server.ipynb
+notebooks/122-quantizing-model-with-accuracy-control/122-speech-recognition-quantization-wav2vec2.ipynb
+notebooks/122-quantizing-model-with-accuracy-control/122-yolov8-quantization-with-accuracy-control.ipynb
 notebooks/211-speech-to-text/211-speech-to-text.ipynb
 notebooks/214-grammar-correction/214-grammar-correction.ipynb
 notebooks/215-image-inpainting/215-image-inpainting.ipynb
+notebooks/220-cross-lingual-books-alignment/220-cross-lingual-books-alignment.ipynb
 notebooks/225-stable-diffusion-text-to-image/225-stable-diffusion-text-to-image.ipynb
+notebooks/227-whisper-subtitles-generation/227-whisper-convert.ipynb
+notebooks/227-whisper-subtitles-generation/227-whisper-nncf-quantize.ipynb
 notebooks/228-clip-zero-shot-image-classification/228-clip-zero-shot-convert.ipynb
 notebooks/228-clip-zero-shot-image-classification/228-clip-zero-shot-quantize.ipynb
-notebooks/230-yolov8-optimization/230-yolov8-optimization.ipynb
+notebooks/230-yolov8-optimization/230-yolov8-instance-segmentation.ipynb
+notebooks/230-yolov8-optimization/230-yolov8-keypoint-detection.ipynb
+notebooks/230-yolov8-optimization/230-yolov8-object-detection.ipynb
 notebooks/231-instruct-pix2pix-image-editing/231-instruct-pix2pix-image-editing.ipynb
+notebooks/232-clip-language-saliency-map/232-clip-language-saliency-map.ipynb
+notebooks/233-blip-visual-language-processing/233-blip-optimize.ipynb
+notebooks/233-blip-visual-language-processing/233-blip-convert.ipynb
 notebooks/235-controlnet-stable-diffusion/235-controlnet-stable-diffusion.ipynb
 notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-infinite-zoom.ipynb
 notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-text-to-image.ipynb
 notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-optimum-demo-comparison.ipynb
 notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-optimum-demo.ipynb
 notebooks/236-stable-diffusion-v2/236-stable-diffusion-v2-text-to-image-demo.ipynb
 notebooks/237-segment-anything/237-segment-anything.ipynb
-notebooks/237-segment-anything/237-segment-anything-fiftyone.ipynb
-notebooks/238-deeployd-if/238-deep-floyd-if.ipynb
-notebooks/239-image-bind/239-image-bind.ipynb
+notebooks/238-deepfloyd-if/238-deep-floyd-if-convert.ipynb
+notebooks/238-deepfloyd-if/238-deep-floyd-if-optimize.ipynb
+notebooks/239-image-bind/239-image-bind-convert.ipynb
+notebooks/239-image-bind/239-image-bind-quantize.ipynb
 notebooks/240-dolly-2-instruction-following/240-dolly-2-instruction-following.ipynb
 notebooks/241-riffusion-text-to-music/241-riffusion-text-to-music.ipynb
+notebooks/244-named-entity-recognition/244-named-entity-recognition.ipynb
 notebooks/248-stable-diffusion-xl/248-stable-diffusion-xl.ipynb
+notebooks/248-stable-diffusion-xl/248-segmind-vegart.ipynb
+notebooks/248-stable-diffusion-xl/248-ssd-b1.ipynb
+notebooks/249-oneformer-segmentation/249-oneformer-segmentation.ipynb
+notebooks/251-tiny-sd-image-generation/251-tiny-sd-image-generation.ipynb
+notebooks/252-fastcomposer-image-generation/252-fastcomposer-image-generation.ipynb
+notebooks/253-zeroscope-text2video/253-zeroscope-text2video.ipynb
+notebooks/254-llm-chatbot/254-llm-chatbot.ipynb
+notebooks/254-llm-chatbot/254-rag-chatbot.ipynb
+notebooks/255-mms-massively-multilingual-speech/255-mms-massively-multilingual-speech.ipynb
+notebooks/256-bark-text-to-audio/256-bark-text-to-audio.ipynb
+notebooks/257-llava-multimodal-chatbot/257-llava-multimodal-chatbot.ipynb
+notebooks/257-llava-multimodal-chatbot/257-videollava-multimodal-chatbot.ipynb
+notebooks/258-blip-diffusion-subject-generation/258-blip-diffusion-subject-generation.ipynb
+notebooks/259-decidiffusion-image-generation/259-decidiffusion-image-generation.ipynb
+notebooks/260-pix2struct-docvqa/260-pix2struct-docvqa.ipynb
+notebooks/262-softvc-voice-conversion/262-softvc-voice-conversion.ipynb
+notebooks/263-latent-consistency-models-image-generation/263-latent-consistency-models-image-generation.ipynb
+notebooks/263-latent-consistency-models-image-generation/263-lcm-lora-controlnet.ipynb
+notebooks/264-qrcode-monster/264-qrcode-monster.ipynb
+notebooks/265-wuerstchen-image-generation/265-wuerstchen-image-generation.ipynb
+notebooks/266-speculative-sampling/266-speculative-sampling.ipynb
+notebooks/267-distil-whisper-asr/267-distil-whisper-asr.ipynb
+notebooks/269-film-slowmo/269-film-slowmo.ipynb
+notebooks/270-sound-generation-audioldm2/270-sound-generation-audioldm2.ipynb
+notebooks/271-sdxl-turbo/271-sdxl-turbo.ipynb
+notebooks/272-paint-by-example/272-paint-by-example.ipynb
+notebooks/273-stable-zephyr-3b-chatbot/273-stable-zephyr-3b-chatbot.ipynb
+notebooks/275-llm-question-answering/275-llm-question-answering.ipynb
 notebooks/404-style-transfer-webcam/404-style-transfer.ipynb

.ci/ignore_pip_conflicts.txt

@@ -0,0 +1,17 @@
+notebooks/109-performance-tricks/109-latency-tricks.ipynb  # ultralytics<=8.0.178
+notebooks/109-performance-tricks/109-throughput-tricks.ipynb  # ultralytics<=8.0.178
+notebooks/123-detectron2-to-openvino/123-detectron2-to-openvino.ipynb # detectron2@https://github.com/facebookresearch/detectron2
+notebooks/122-quantizing-model-with-accuracy-control/122-yolov8-quantization-with-accuracy-control.ipynb  # ultralytics==8.0.43
+notebooks/204-segmenter-semantic-segmentation/204-segmenter-semantic-segmentation.ipynb # timm==0.4.12, install Segmenter requirements
+notebooks/212-pyannote-speaker-diarization/212-pyannote-speaker-diarization.ipynb  # pyannote-audio@https://github.com/eaidova/pyannote-audio
+notebooks/230-yolov8-optimization/230-yolov8-instance-segmentation.ipynb  # ultralytics==8.0.43
+notebooks/230-yolov8-optimization/230-yolov8-keypoint-detection.ipynb  # ultralytics==8.0.159
+notebooks/230-yolov8-optimization/230-yolov8-object-detection.ipynb  # ultralytics==8.0.43
+notebooks/254-llm-chatbot/254-llm-chatbot.ipynb # nncf@https://github.com/openvinotoolkit/nncf/tree/release_v280
+notebooks/254-llm-chatbot/254-rag-chatbot.ipynb # nncf@https://github.com/openvinotoolkit/nncf/tree/release_v280
+notebooks/256-bark-text-to-audio/256-bark-text-to-audio.ipynb  # torch==1.13
+notebooks/257-llava-multimodal-chatbot/257-llava-multimodal-chatbot.ipynb # transformers<4.35
+notebooks/257-llava-multimodal-chatbot/257-videollava-multimodal-chatbot.ipynb # transformers<4.35
+notebooks/273-stable-zephyr-3b-chatbot/273-stable-zephyr-3b-chatbot.ipynb # install requirements.txt after clone repo
+notebooks/279-mobilevlm-language-assistant/279-mobilevlm-language-assistant.ipynb # transformers<4.35
+notebooks/280-depth-anything/280-depth-anything.ipynb # install requirements.txt after clone repo

.ci/ignore_treon_docker.txt

@@ -1,16 +1,51 @@
 107-speech-recognition-quantization
 108-gpu-device
 117-model-server
+122-quantizing-model-with-accuracy-control
+204-segmenter-semantic-segmentation
+216-attention-center
+220-cross-lingual-books-alignment
 225-stable-diffusion-text-to-image
+227-whisper-subtitles-generation
 231-instruct-pix2pix-image-editing
+234-encodec-audio-compression
 235-controlnet-stable-diffusion
 236-stable-diffusion-v2
 237-segment-anything
-238-deeployd-if
+238-deepfloyd-if
 239-image-bind
 240-dolly-2-instruction-following
 241-riffusion-text-to-music
+242-freevc-voice-conversion
+247-code-language-id
 248-stable-diffusion-xl
+249-oneformer-segmentation
+250-music-generation
+251-tiny-sd-image-generation
+252-fastcomposer-image-generation
+253-zeroscope-text2video
+254-llm-chatbot
+255-mms-massively-multilingual-speech
+256-bark-text-to-audio
+257-llava-multimodal-chatbot
+258-blip-diffusion-subject-generation
+259-decidiffusion-image-generation
+260-pix2struct-docvqa
+261-fast-segment-anything
+262-softvc-voice-conversion
+263-latent-consistency-models-image-generation
+264-qrcode-monster
+265-wuerstchen-image-generation
+266-speculative-sampling
+267-distil-whisper-asr
+269-film-slowmo
+270-sound-generation-audioldm2
+271-sdxl-turbo
+272-paint-by-example
+273-stable-zephyr-3b-chatbot
+276-stable-diffusion-torchdynamo-backend
+281-kosmos2-multimodal-large-language-model
+283-photo-maker
 301-tensorflow-training-openvino
 305-tensorflow-quantization-aware-training
 404-style-transfer-webcam

.ci/ignore_treon_linux.txt

@@ -1,14 +1,52 @@
 107-speech-recognition-quantization
 108-gpu-device
+112-pytorch-post-training-quantization-nncf
 117-model-server
+122-quantizing-model-with-accuracy-control
+204-segmenter-semantic-segmentation
+214-grammar-correction
+216-attention-center
+220-cross-lingual-books-alignment
 225-stable-diffusion-text-to-image
+226-yolov7-optimization
+227-whisper-subtitles-generation
 231-instruct-pix2pix-image-editing
+234-encodec-audio-compression
 235-controlnet-stable-diffusion
 236-stable-diffusion-v2
 237-segment-anything
-238-deeployd-if
+238-deepfloyd-if
 239-image-bind
 240-dolly-2-instruction-following
 241-riffusion-text-to-music
+242-freevc-voice-conversion
+247-code-language-id
 248-stable-diffusion-xl
-404-style-transfer-webcam
+249-oneformer-segmentation
+250-music-generation
+251-tiny-sd-image-generation
+252-fastcomposer-image-generation
+253-zeroscope-text2video
+254-llm-chatbot
+255-mms-massively-multilingual-speech
+256-bark-text-to-audio
+257-llava-multimodal-chatbot
+258-blip-diffusion-subject-generation
+259-decidiffusion-image-generation
+260-pix2struct-docvqa
+261-fast-segment-anything
+262-softvc-voice-conversion
+263-latent-consistency-models-image-generation
+264-qrcode-monster
+265-wuerstchen-image-generation
+266-speculative-sampling
+267-distil-whisper-asr
+269-film-slowmo
+270-sound-generation-audioldm2
+271-sdxl-turbo
+272-paint-by-example
+273-stable-zephyr-3b-chatbot
+276-stable-diffusion-torchdynamo-backend
+281-kosmos2-multimodal-large-language-model
+283-photo-maker
+404-style-transfer-webcam

.ci/ignore_treon_mac.txt

@@ -1,15 +1,50 @@
 107-speech-recognition-quantization
 108-gpu-device
 117-model-server
+122-quantizing-model-with-accuracy-control
+204-segmenter-semantic-segmentation
+216-attention-center
+220-cross-lingual-books-alignment
 225-stable-diffusion-text-to-image
+227-whisper-subtitles-generation
 231-instruct-pix2pix-image-editing
+234-encodec-audio-compression
 235-controlnet-stable-diffusion
 236-stable-diffusion-v2
 237-segment-anything
-238-deeployd-if
+238-deepfloyd-if
 239-image-bind
 240-dolly-2-instruction-following
 241-riffusion-text-to-music
 242-freevc-voice-conversion
+247-code-language-id
 248-stable-diffusion-xl
+249-oneformer-segmentation
+250-music-generation
+251-tiny-sd-image-generation
+252-fastcomposer-image-generation
+253-zeroscope-text2video
+254-llm-chatbot
+255-mms-massively-multilingual-speech
+256-bark-text-to-audio
+257-llava-multimodal-chatbot
+258-blip-diffusion-subject-generation
+259-decidiffusion-image-generation
+260-pix2struct-docvqa
+261-fast-segment-anything
+262-softvc-voice-conversion
+263-latent-consistency-models-image-generation
+264-qrcode-monster
+265-wuerstchen-image-generation
+266-speculative-sampling
+267-distil-whisper-asr
+269-film-slowmo
+270-sound-generation-audioldm2
+271-sdxl-turbo
+272-paint-by-example
+273-stable-zephyr-3b-chatbot
+276-stable-diffusion-torchdynamo-backend
+281-kosmos2-multimodal-large-language-model
+279-mobilevlm-language-assistant
+283-photo-maker
 404-style-transfer-webcam