Hugging Face's logo

sergiopaniego
/
OptimizedPilotNet

TF-Keras
TF Lite
Model card Files Community
sergiopaniego commited on
Commit
222d844
•
1 Parent(s): eb4fde0

Updated PyTorch optimized models

Browse files
Files changed (9) hide show
  1. README.md +6 -6
  2. pytorch/{28_04_dynamic_quan.pth → 24_05_dynamic_quan.pth} +2 -2
  3. pytorch/{28_04_global_prune.pth → 24_05_global_prune.pth} +2 -2
  4. pytorch/{28_04_local_prune.pth → 24_05_local_prune.pth} +2 -2
  5. pytorch/{28_04_prune_quan.pth → 24_05_prune_quan.pth} +2 -2
  6. pytorch/24_05_quan_aware.pth +3 -0
  7. pytorch/24_05_static_quan.pth +3 -0
  8. pytorch/28_04_quan_aware.pth +0 -3
  9. pytorch/28_04_static_quan.pth +0 -3
README.md CHANGED
@@ -61,12 +61,12 @@ To do inference:
61
  | Optimization | Model size (MB) | MSE | Inference time (s/frame) | Filename |
62
  | --------------------------------- | ---------------------- | ---------------------- | ---------------------- | --------------------------------- |
63
  | Original | 6.1217 | 0.03524 | - | 28_04_pilot_net_model_best_123.pth |
64
- | Dynamic Range Quantization | 1.9493608474731445 | 0.012065857842182075 | 0.001480283498764038 | 28_04_dynamic_quan.pth |
65
- | Static Quantization | 1.6071176528930664 | 0.012072610909984047 | 0.0007314345836639404 | 28_04_static_quan.pth |
66
- | Quantization Aware Training | 1.6069536209106445 | 0.01109830549109022 | 0.0011710402965545653 | 28_04_quan_aware.pth |
67
- | Local Prune | 6.122584342956543 | 0.010850968803449539 | 0.0014387350082397461 | 28_04_local_prune.pth |
68
- | Global Prune | 6.122775077819824 | 0.010964057565769462 | 0.0014179635047912597 | 28_04_global_prune.pth |
69
- | Prune + Quantization | 1.6067094802856445 | 0.010949893930274941 | 0.0011728739738464356 | 28_04_prune_quan.pth |
70
 
71
  TensorRT-PyTorch:
72
 
 
61
  | Optimization | Model size (MB) | MSE | Inference time (s/frame) | Filename |
62
  | --------------------------------- | ---------------------- | ---------------------- | ---------------------- | --------------------------------- |
63
  | Original | 6.1217 | 0.03524 | - | 28_04_pilot_net_model_best_123.pth |
64
+ | Dynamic Range Quantization | 1.9493608474731445 | 0.012065857842182075 | 0.001480283498764038 | 24_05_dynamic_quan.pth |
65
+ | Static Quantization | 1.6071176528930664 | 0.012072610909984047 | 0.0007314345836639404 | 24_05_static_quan.pth |
66
+ | Quantization Aware Training | 1.6069536209106445 | 0.01109830549109022 | 0.0011710402965545653 | 24_05_quan_aware.pth |
67
+ | Local Prune | 6.122584342956543 | 0.010850968803449539 | 0.0014387350082397461 | 24_05_local_prune.pth |
68
+ | Global Prune | 6.122775077819824 | 0.010964057565769462 | 0.0014179635047912597 | 24_05_global_prune.pth |
69
+ | Prune + Quantization | 1.6067094802856445 | 0.010949893930274941 | 0.0011728739738464356 | 24_05_prune_quan.pth |
70
 
71
  TensorRT-PyTorch:
72
 
pytorch/{28_04_dynamic_quan.pth → 24_05_dynamic_quan.pth} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef6b2f26a335265ce6a1f70d5634086005d3304b3d4d0ce81c7a4b7ae309a829
3
- size 2041305
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c4bf54306eaae46363f68daffd6939976fd29bd254ea8c544ee0ba14669b10
3
+ size 2044053
pytorch/{28_04_global_prune.pth → 24_05_global_prune.pth} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec6a143cb9811e594f5776b2e25d47cce3574abf01a4a8b6945aa5b8effb4cd9
3
- size 6417487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efd09eb174e5b53bb852ff4077edc06bed653b09d067d14bad6e2fa2b0cd94f9
3
+ size 6420195
pytorch/{28_04_local_prune.pth → 24_05_local_prune.pth} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d92f2f47f8c870e4abca2b1a591a4c6a0072b3d1820e0b021f126c84e057d45
3
- size 6417415
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e8084fd6e27d13e38b48739aafcec9b37d0a26aaf0292debdb1babe857fb86
3
+ size 6419995
pytorch/{28_04_prune_quan.pth → 24_05_prune_quan.pth} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8678e67d0c0a2cf2c3eb05514e9c43bc80008750972ef1e6df4ab83ee44c1e8e
3
- size 1684785
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0bc84d7abc58b7780d63d19f66b10dd33d560bde8c792ee2de2a46a5d7fd44
3
+ size 1684757
pytorch/24_05_quan_aware.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ac20676197d4226dfea9138d382a9367525868f968ec1f8563043a829e4aad
3
+ size 1685013
pytorch/24_05_static_quan.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58bed2cd38bee2c76a10910be4a0170c03dcbe779dac424d4645cb0e45ec07b3
3
+ size 1685185
pytorch/28_04_quan_aware.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a0d7e6eb1803060d032a0be87c50296809b8432609ae784dac9668dab3dc976
3
- size 1684785
 
 
 
 
pytorch/28_04_static_quan.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f52fa032df8d3e9008feca8e928049296dd9f89efc003aeef28139f5456114b3
3
- size 1682999