End of training

README.md

@@ -16,29 +16,29 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [PekingU/rtdetr_v2_r50vd](https://huggingface.co/PekingU/rtdetr_v2_r50vd) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 11.9610
-- Map: 0.3649
-- Map 50: 0.6413
-- Map 75: 0.3314
-- Map Small: 0.3681
-- Map Medium: 0.3514
-- Map Large: 0.5909
-- Mar 1: 0.315
-- Mar 10: 0.5779
-- Mar 100: 0.6508
-- Mar Small: 0.4932
-- Mar Medium: 0.5762
-- Mar Large: 0.784
-- Map Coverall: 0.5504
-- Mar 100 Coverall: 0.8538
-- Map Face Shield: 0.3497
-- Mar 100 Face Shield: 0.7471
-- Map Gloves: 0.2505
-- Mar 100 Gloves: 0.4915
-- Map Goggles: 0.2357
-- Mar 100 Goggles: 0.5655
-- Map Mask: 0.4385
-- Mar 100 Mask: 0.5961
+- Loss: 15.7596
+- Map: 0.243
+- Map 50: 0.4016
+- Map 75: 0.2288
+- Map Small: 0.1622
+- Map Medium: 0.1679
+- Map Large: 0.4047
+- Mar 1: 0.2498
+- Mar 10: 0.5329
+- Mar 100: 0.6054
+- Mar Small: 0.4114
+- Mar Medium: 0.5602
+- Mar Large: 0.781
+- Map Coverall: 0.4109
+- Mar 100 Coverall: 0.7821
+- Map Face Shield: 0.1194
+- Mar 100 Face Shield: 0.6471
+- Map Gloves: 0.2443
+- Mar 100 Gloves: 0.4508
+- Map Goggles: 0.065
+- Mar 100 Goggles: 0.4586
+- Map Mask: 0.3754
+- Mar 100 Mask: 0.6882
 
 ## Model description
 
@@ -64,22 +64,19 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 300
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Map    | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1  | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:------------:|:----------------:|:---------------:|:-------------------:|:----------:|:--------------:|:-----------:|:---------------:|:--------:|:------------:|
-| No log        | 1.0   | 107  | 55.3917         | 0.0232 | 0.0485 | 0.0213 | 0.0       | 0.0062     | 0.0249    | 0.04   | 0.0855 | 0.0943  | 0.0       | 0.0516     | 0.1121    | 0.1087       | 0.3068           | 0.0004          | 0.0519              | 0.0001     | 0.0085         | 0.0         | 0.0277          | 0.0069   | 0.0769       |
-| No log        | 2.0   | 214  | 28.9185         | 0.1144 | 0.2063 | 0.1092 | 0.0122    | 0.0769     | 0.1746    | 0.1466 | 0.267  | 0.2858  | 0.0174    | 0.2233     | 0.5011    | 0.3659       | 0.6144           | 0.0255          | 0.238               | 0.0138     | 0.1277         | 0.0502      | 0.2092          | 0.1164   | 0.2396       |
-| No log        | 3.0   | 321  | 19.5631         | 0.1944 | 0.363  | 0.1809 | 0.1027    | 0.1483     | 0.2848    | 0.2424 | 0.4058 | 0.4504  | 0.2156    | 0.4032     | 0.654     | 0.4834       | 0.6883           | 0.0884          | 0.4747              | 0.0624     | 0.2429         | 0.0624      | 0.3692          | 0.2753   | 0.4769       |
-| No log        | 4.0   | 428  | 15.2810         | 0.2345 | 0.4587 | 0.2098 | 0.1045    | 0.1855     | 0.4544    | 0.2525 | 0.4567 | 0.5091  | 0.2361    | 0.4726     | 0.734     | 0.551        | 0.7279           | 0.1186          | 0.543               | 0.1237     | 0.417          | 0.1106      | 0.3846          | 0.2685   | 0.4729       |
-| 55.6421       | 5.0   | 535  | 14.7773         | 0.2391 | 0.4678 | 0.2144 | 0.0671    | 0.1875     | 0.447     | 0.2633 | 0.4649 | 0.5141  | 0.2299    | 0.4817     | 0.7456    | 0.5519       | 0.7369           | 0.1398          | 0.5443              | 0.114      | 0.3906         | 0.1052      | 0.4262          | 0.2844   | 0.4724       |
+| No log        | 1.0   | 107  | 35.1046         | 0.0395 | 0.0911 | 0.0256 | 0.0015    | 0.0104     | 0.0475    | 0.0733 | 0.1851 | 0.2494  | 0.0421    | 0.1906     | 0.365     | 0.1668       | 0.5491           | 0.0207          | 0.2278              | 0.0068     | 0.1759         | 0.0007      | 0.0877          | 0.0024   | 0.2062       |
+| No log        | 2.0   | 214  | 18.0639         | 0.1779 | 0.3283 | 0.1719 | 0.0679    | 0.1        | 0.2844    | 0.2053 | 0.4086 | 0.4734  | 0.2576    | 0.3816     | 0.7174    | 0.4958       | 0.7032           | 0.0485          | 0.4873              | 0.1107     | 0.3246         | 0.0257      | 0.3754          | 0.2086   | 0.4764       |
 
 
 ### Framework versions
 
 - Transformers 4.50.0.dev0
 - Pytorch 2.6.0+cu124
-- Datasets 3.3.2
-- Tokenizers 0.21.0
+- Datasets 3.4.1
+- Tokenizers 0.21.1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "PekingU/rtdetr_v2_r50vd",
   "activation_dropout": 0.0,
   "activation_function": "silu",
   "anchor_image_size": null,
@@ -10,7 +9,25 @@
   "auxiliary_loss": true,
   "backbone": null,
   "backbone_config": {
+    "depths": [
+      3,
+      4,
+      6,
+      3
+    ],
+    "downsample_in_bottleneck": false,
+    "downsample_in_first_stage": false,
+    "embedding_size": 64,
+    "hidden_act": "relu",
+    "hidden_sizes": [
+      256,
+      512,
+      1024,
+      2048
+    ],
+    "layer_type": "bottleneck",
     "model_type": "rt_detr_resnet",
+    "num_channels": 3,
     "out_features": [
       "stage2",
       "stage3",
@@ -20,6 +37,13 @@
       2,
       3,
       4
+    ],
+    "stage_names": [
+      "stem",
+      "stage1",
+      "stage2",
+      "stage3",
+      "stage4"
     ]
   },
   "backbone_kwargs": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fc01619d86b0aa46ae0981942d0ab85500f02c5662afc0a8d5d01b33cb8e2c
+oid sha256:9089859ca89f23d5b0716db7d4fcafd09b4246d26226e3daea160ba96e24b3fe
 size 171560340

runs/Mar17_17-01-32_234beae8f979/events.out.tfevents.1742230897.234beae8f979.4375.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a648caa31d4698816585e863aace57530ecca69e28bca8ec12128e3afeb74af
+size 10454

runs/Mar17_17-01-32_234beae8f979/events.out.tfevents.1742231103.234beae8f979.4375.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64bbfe303afa059293bd06f842cc3166c4076a8265b5160548a3602706662f5d
+size 1548

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70eaa74dc024fd4428a98302da9b01fadad4ad997b3464bdc9bb94137c9c97d8
+oid sha256:260b5be58396f9e90d42898fc0657884dab08407e1ffcbf17676a4d09048dfa2
 size 5368