Study on the Collaborative Acceleration Method Between CPU and GPU in Image Processing of Mask Detectio
Bibliographic record
Abstract
The image processing methods of the current big data volume are based on parallel computing to improve the processing speed. There are two ways of mainstream parallel image processing, one is to use DSP or FPGA parallel processing, and the other is to use GPU-based CUDA parallel distributed system. DSP or FPGA parallel image processing mode can realize the complex operation, the fast and low power consumption, but the development is difficult, the developer needs to be familiar with the hardware and software knowledge, write algorithms for different hardware structure, program portability is very poor and the development cycle is long. In GPU-based CUDA parallel processing system, the GPU is responsible for performing highly threaded image parallel processing tasks, the CPU is responsible for logical image processing and serial computing, and the CPU and GPU work together. GPU as a coprocessor, low power consumption, large memory and transmission capacity, currently fully support C and C language, easy to develop and because of the hardware structure fixed algorithm portability is high. The GPU parallel processing technology, with its unique multi-threaded architecture acceleration model, plays an important role in improving the speed of mask defect detection and processing.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".