Delete README.md

README.md

@@ -1,29 +0,0 @@
----
-datasets:
-  - PASCAL-VOC
-language:
-  - en
-metrics:
-  - mAP
-library_name: pytorch
-pipeline_tag: object-detection
-tags:
-- faster-rcnn
-- object-detection
-- pytorch
-- computer-vision
-- from-scratch
-- paper-implementation
-
-results:
- - Metric Result
- - mAP@0.5  63% 
- - RPN Recall @ IoU 0.5 - 83%
-
-Known_Deviations(expected affect on mAP):
- -ResNet-50 instead of ResNet-101 due to compute constraint resulting weaker features than ResNet-101, likely costing several mAP points — probably felt most on small/textured classes like `bottle`/`pottedplant`, this project's weakest. Not isolated by a ResNet-101 run.
- -Batch size 2 instead of 1, GPU throughput, Paper's lr schedule (per-image, batch size 1) reused unscaled, changing gradient noise per step. Not isolated.
- -No horizontal flip augmentation, not implemented, Paper's VOC recipe uses flipping as a free 2× augmentation; skipping it likely costs some mAP, more on sparser classes. Not isolated.
- -BatchNorm frozen from Step 2 onward, Batch size 2 is too small for stable BN statistics — standard practice, not ad hoc, Expected neutral-to-beneficial vs. unfrozen (paper's VGG16 has no BN to compare against). Step 1 is the exception — its backbone trains with BN unfrozen.
-
----