Ultralytics 8.4.21  Python-3.12.6 torch-2.9.1+cpu CPU (12th Gen Intel Core i5-12500)
WARNING 'nms=True' is not available for end2end models. Forcing 'nms=False'.
YOLO26n summary (fused): 122 layers, 2,376,006 parameters, 0 gradients, 5.2 GFLOPs

PyTorch: starting from 'best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 300, 6) (14.8 MB)

TensorFlow SavedModel: starting export with tensorflow 2.19.1...
TensorFlow SavedModel: collecting INT8 calibration images from 'data=unified_dataset/data.yaml'
Fast image access  (ping: 0.10.1 ms, read: 181.197.3 MB/s, size: 81.4 KB)

Scanning E:\Task\Research and Development\palm-oil-ai\unified_dataset\labels\val.cache... 2756 images, 0 backgrounds, 0 corrupt: 100% ΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöü 2756/2756  0.0s
val: E:\Task\Research and Development\palm-oil-ai\unified_dataset\images\val\suharjito_dataset_framesawit27--11-_png.rf.78949fb137da444431f25b2a8c330315.jpg: 1 duplicate labels removed
val: E:\Task\Research and Development\palm-oil-ai\unified_dataset\images\val\suharjito_dataset_frameterlalumasak12--3-_png.rf.14cc4ac1908d88702451ec53d52c5f35.jpg: 1 duplicate labels removed
WARNING Box and segment counts should be equal, but got len(segments) = 165, len(boxes) = 7378. To resolve this only boxes will be used and all segments will be removed. To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset.

ONNX: starting export with onnx 1.20.1 opset 22...
python : C:\Users\enzo\
AppData\Roaming\Python\
Python312\site-packages
\torch\onnx\_internal\t
orchscript_exporter\uti
ls.py:1447: 
OnnxExporterWarning: 
Exporting to ONNX 
opset version 22 is 
not supported. by 
'torch.onnx.export()'. 
The highest opset 
version supported is 
20. To use a newer 
opset version, 
consider 'torch.onnx.ex
port(..., 
dynamo=True)'. 
At line:1 char:1
+ python 
export_mobile.py > 
export_log.txt 2>&1
+ ~~~~~~~~~~~~~~~~~~~~~
~~~~~~~~~~~~~~~~~~~~~~~
~
    + CategoryInfo     
         : NotSpecifi  
  ed: (C:\Users\enzo   
 \A...dynamo=True)'    
. :String) [], Rem    
oteException
    + FullyQualifiedEr 
   rorId : NativeComm  
  andError
 
  warnings.warn(
C:\Users\enzo\AppData\R
oaming\Python\Python312
\site-packages\torch\on
nx\_internal\torchscrip
t_exporter\symbolic_ops
et9.py:5353: 
UserWarning: Exporting 
aten::index operator 
of advanced indexing 
in opset 22 is 
achieved by 
combination of 
multiple ONNX 
operators, including 
Reshape, Transpose, 
Concat, and Gather. If 
indices include 
negative values, the 
exported graph will 
produce incorrect 
results.
  warnings.warn(
ONNX: slimming with onnxslim 0.1.87...
ONNX: export success  5.2s, saved as 'best.onnx' (9.5 MB)

Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 4% ΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇ 40.0KB/1.1MB 60.3KB/s 0.2s<18.2s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 9% ΓöüΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇ 104.0KB/1.1MB 140.9KB/s 0.4s<7.3s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 20% ΓöüΓöüΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇ 232.0KB/1.1MB 302.9KB/s 0.6s<3.0s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 37% ΓöüΓöüΓöüΓöüΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇ 424.0KB/1.1MB 1.8MB/s 0.7s<0.4s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 44% ΓöüΓöüΓöüΓöüΓöüΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇΓöÇ 504.0KB/1.1MB 432.8KB/s 0.8s<1.5s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 82% ΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓò╕ΓöÇΓöÇ 936.0KB/1.1MB 4.0MB/s 0.9s<0.0s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 96% ΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓò╕ 1.1/1.1MB 1.5MB/s 1.0s<0.0s
Downloading https://github.com/ultralytics/assets/releases/download/v8.4.0/calibration_image_sample_data_20x128x128x3_float32.npy.zip to 'calibration_image_sample_data_20x128x128x3_float32.npy.zip': 100% ΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöü 1.1MB 1.1MB/s 1.0s

Unzipping calibration_image_sample_data_20x128x128x3_float32.npy.zip to E:\Task\Research and Development\palm-oil-ai\calibration_image_sample_data_20x128x128x3_float32.npy...: 100% ΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöüΓöü 1/1 38.3files/s 0.0s
WARNING:tensorflow:From
 C:\Users\enzo\AppData\
Roaming\Python\Python31
2\site-packages\tf_kera
s\src\losses.py:2976: 
The name tf.losses.spar
se_softmax_cross_entrop
y is deprecated. 
Please use tf.compat.v1
.losses.sparse_softmax_
cross_entropy instead.

TensorFlow SavedModel: starting TFLite export with onnx2tf 1.28.8...