ScaledYOLOv4 port to Polaris #335
Open
Conversation
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
ramamalladiTT
requested review from
jajuTT,
ssapreTT and
vmgeorgeTT
as code owners
Contributor
There was a problem hiding this comment.
Pull request overview
This pull request ports the ScaledYOLOv4 object detection model to the Polaris platform using ttsim (TensTorrent Simulator). The PR adds comprehensive validation infrastructure comparing ttsim implementations against PyTorch reference implementations.
Changes:
- Adds ScaledYOLOv4 model implementation with ttsim-compatible modules
- Implements validation scripts for 18+ common modules and 2 YOLO-specific modules
- Extends ttsim core to support data propagation through operations (Conv2d, BatchNorm, MaxPool, etc.)
- Adds new operations (Mish, ReLU6, AdaptiveAvgPool2d) to ttsim
- Includes configuration files for workload registration
Reviewed changes
Copilot reviewed 38 out of 38 changed files in this pull request and generated 26 comments.
Show a summary per file
| File | Description |
|---|---|
| workloads/ScaledYOLOv4/reference/yolo/run_all.py | Orchestrates YOLO module validations (Detect, Model) |
| workloads/ScaledYOLOv4/reference/yolo/results.md | Pre-generated validation results (2/2 modules passed) |
| workloads/ScaledYOLOv4/reference/yolo/detect.py | Validates Detect layer against PyTorch |
| workloads/ScaledYOLOv4/reference/common/run_all.py | Orchestrates common module validations (18 modules) |
| workloads/ScaledYOLOv4/reference/common/results.md | Pre-generated validation results (18/18 passed) |
| workloads/ScaledYOLOv4/reference/common/*.py | Individual module validation scripts |
| workloads/ScaledYOLOv4/models/experimental.py | Experimental modules (CrossConv, C3, GhostConv, etc.) |
| workloads/ScaledYOLOv4/models/utils/*.py | Utility functions adapted for ttsim |
| workloads/ScaledYOLOv4/README.md | Documentation for workload validation |
| ttsim/ops/desc/*.py | Core ttsim extensions for data propagation |
| ttsim/front/functional/op.py | New operation definitions (Mish, ReLU6, AdaptiveAvgPool2d) |
| config/*.yaml | Configuration for workload registration |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
ramamalladiTT
force-pushed
the
scaledyolov4
branch
from
6ce1cf1 to
e8d2fc5
Compare
Contributor
|
Can some tests be added to test this content? Test Categories:
Across all these categories:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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.