Implement Model A (standard CNN)
Nobody has claimed this yet.
Assessment
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Newbie friendliness
- 68/100
- Issue type
- Feature
- Clarity
- Clearly specified
- Activity status
- Active
- Tech stack
- python, pytorch
- Domain
- machine-learning
Research direction
Work in src/models.py and build ModelA from the conv_bn helper that issue #12 introduces, so check whether #12 is merged first. Stack four Conv3x3-BN-ReLU-MaxPool blocks with widths 32/64/128/256, then nn.AdaptiveAvgPool2d(1), Dropout(0.3), Dense(64), ReLU and Dense(3). Done when a (2,3,64,64) input returns shape (2,3) and the trainable parameter count is about 405k.
Written by the indexing model from the issue text.
Description
4 x [Conv3x3-BN-ReLU-MaxPool] with widths 32/64/128/256 -> GAP -> Dropout(0.3) -> Dense(64) -> ReLU -> Dense(3).
Files: src/models.py
Tasks
-
class ModelA(nn.Module)built fromconv_bn - Use
nn.AdaptiveAvgPool2d(1)(GAP) instead of Flatten - Docstring listing the output shape after each stage
Done when
Forward of (2,3,64,64) returns (2,3); about 405k trainable parameters.
Depends on
#12
Close with a commit or PR message containing Closes #<this issue>.
- Dominant language
- Jupyter Notebook
- Stars
- 0
- Forks
- 0
- Avg merge
- 1m
- Merged PRs (30d)
- 3
Getting set up
This project ships no dev container, Dockerfile or contributing guide, so setting up is up to you: start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from VisionForgeCSE/CNN-For-Image-Classification
-
evaluation
Difficulty 2/5 1-3 hours Newbie friendliness 66/100
-
evaluation good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
-
evaluation
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
training
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Optimizer factoryOpentraining
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
All issues in VisionForgeCSE/CNN-For-Image-Classification
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
huggingface/peft#3955 ·
Maintainers usually reply within 1 day
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
huggingface/transformers#49556 ·
Maintainers usually reply within 1 day
-
bug embedded exports
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
ultralytics/ultralytics#26655 · 2 comments ·
Maintainers usually reply within 1 day
-
enhancement needs-acceptance wg/router-models-inference-runtime
Difficulty 2/5 1-3 hours Newbie friendliness 76/100
vllm-project/semantic-router#5015 · 1 comment ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 77/100
Maintainers usually reply within 2 days