【25-Q3-生态建设】模型迁移-研发效能部-模型训练-在PyTorch框架上支持continual-learning在MNIST数据集上的训练

PyTorch/build-in/other/continual-learning/Dockerfile

@@ -0,0 +1,12 @@
+ARG FROM_IMAGE_NAME=jfrog.tecorigin.net/tecotp-docker/release/ubuntu22.04/x86_64/pytorch:2.1.1-torch_sdaa2.1.1
+FROM ${FROM_IMAGE_NAME}
+
+WORKDIR /workspace/
+ADD requirements.txt /workspace/
+RUN rm -rf /bin/sh && ln -s /bin/bash /bin/sh
+RUN source activate torch_env && pip install --no-cache-dir -r requirements.txt
+ADD . /workspace/other/continual-learning
+WORKDIR /workspace/other/continual-learning
+
+ARG FROM_IMAGE_NAME=jfrog.tecorigin.net/tecotp-docker/release/ubuntu22.04/x86_64/pytorch:2.1.1-torch_sdaa2.1.1
+FROM ${FROM_IMAGE_NAME}

PyTorch/build-in/other/continual-learning/ICLRblogpost/README.md

@@ -0,0 +1,54 @@
+# On the computation of the Fisher Information in continual learning (2025, ICLR Blogpost)
+
+The code in this repository is used for the experiments reported in the
+[ICLR 2025 blog post "On the computation of the Fisher Information in continual learning"](https://iclr-blogposts.github.io/2025/blog/fisher/)
+(or see the arXiv-preprint [here](https://arxiv.org/abs/2502.11756)).
+
+This blog post compares the performance of Elastic Weight Consolidation (EWC) with various different ways of computing the diagonal elements of the Fisher Information matrix.
+The following options are considered:
+- **EXACT**  
+The elements of the Fisher Information are computed exactly. All training samples are used.  
+To use this option: `./main.py --ewc --fisher-labels='all'`
+
+- **EXACT ($n$=500)**  
+The elements of the Fisher Information are computed exactly. Only 500 training samples are used.  
+To use this option: `./main.py --ewc --fisher-labels='all' --fisher-n=500`
+
+- **SAMPLE**  
+The elements of the Fisher Information are estimated using a single Monte Carlo sample. All training samples are used.  
+To use this option: `./main.py --ewc --fisher-labels='sample'`
+
+- **EMPIRICAL**  
+The empirical Fisher Information is used. All training samples are used.  
+To use this option: `./main.py --ewc --fisher-labels='true'`
+
+- **BATCHED ($b$=128)**  
+The empirical Fisher Information is approximated using mini-batches (see blog post for details).  
+To use this option: `./main.py --ewc --fisher-labels='true' --fisher-batch=128`
+
+
+To run the experiments from the blog post, the following lines of code can be used:
+
+```bash
+python3 ICLRblogpost/compare_FI.py --seed=1 --n-seeds=30 --experiment=splitMNIST --scenario=task
+python3 ICLRblogpost/compare_FI.py --seed=1 --n-seeds=30 --experiment=CIFAR10 --scenario=task --reducedResNet --iters=2000 --lr=0.001
+```
+
+
+### Citation
+If this is useful, please consider citing the blog post:
+```
+@inproceedings{vandeven2025fisher,
+  title={On the computation of the {F}isher {I}nformation in continual learning},
+  author={van de Ven, Gido M},
+  booktitle={ICLR Blogposts 2025},
+  year={2025},
+  date={April 28, 2025},
+  url={https://iclr-blogposts.github.io/2025/blog/fisher/}
+}
+```
+
+
+### Acknowledgments
+This project has been supported by a senior postdoctoral fellowship from the
+Resarch Foundation -- Flanders (FWO) under grant number 1266823N.