11:12:14,044 /usr/local/lib/python2.7/dist-packages/iva/ssd/utils/spec_loader.pyc: Merging specification from /project/specs/train.txt 11:12:14,042 /usr/local/lib/python2.7/dist-packages/iva/ssd/utils/spec_loader.pyc: Merging specification from /project/specs/train.txt 11:12:14,020 /usr/local/lib/python2.7/dist-packages/iva/ssd/utils/spec_loader.pyc: Merging specification from /project/specs/train.txt 11:12:13,980 /usr/local/lib/python2.7/dist-packages/iva/ssd/utils/spec_loader.pyc: Merging specification from /project/specs/train.txt 11:12:13,979 /usr/local/lib/python2.7/dist-packages/iva/ssd/utils/spec_loader.pyc: Merging specification from /project/specs/train.txt 11:12:13,957 /usr/local/lib/python2.7/dist-packages/iva/ssd/utils/spec_loader.pyc: Merging specification from /project/specs/train.txt Image_directory_path: "/dataset_processed"Īnd tlt-train console output Using TensorFlow backend. Tfrecords_path: "/dataset_processed/tfrecords/*" 11:11:34,342 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Tfrecords generation complete.įor the dataset_config in the experiment_spec, please use labels in the tfrecords file, while writing the classmap.Īspect_ratios_global: "" 11:11:34,342 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Class map. 11:11:34,342 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO. 11:11:34,342 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Cumulative object statistics 11:11:34,341 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO. 11:11:29,399 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 9 11:11:24,546 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 8 11:11:19,805 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 7 11:11:15,032 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 6 11:11:09,719 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 5 11:11:05,161 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 4 11:11:00,096 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 3 11:10:55,257 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 2 11:10:50,719 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 1 11:10:45,875 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 1, shard 0 11:10:45,875 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO. 11:10:45,091 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 9 11:10:44,223 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 8 11:10:43,381 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 7 11:10:42,606 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 6 11:10:41,783 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 5 11:10:40,973 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 4 11:10:40,115 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 3 11:10:39,053 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 2 11:10:38,272 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 1 Set the encoding, use None for the system default. usr/local/lib/python2.7/dist-packages/iva/detectnet_v2/dataio/kitti_converter_lib.py:266: VisibleDeprecationWarning: Reading unicode strings without specifying the encoding argument is deprecated. 11:10:37,497 - iva.detectnet_v2.dataio.dataset_converter_lib - INFO - Writing partition 0, shard 0 Hence, while choosing the validationset during training choose validation_fold 0. 11:10:37,485 - iva.detectnet_v2.dataio.kitti_converter_lib - INFO - Validation data in partition 0. 11:10:37,485 - iva.detectnet_v2.dataio.kitti_converter_lib - INFO - Num images in 11:10:37,358 - iva.detectnet_v2.dataio.build_converter - INFO - Instantiating a kitti converter Here is the tf-record conversion log: Using TensorFlow backend. Hello, I’m trying to train the SSD model, first I tried with ResNet10 as backbone the training completed successfully.īut, when I switched to SqueezeNet it failed.
0 kommentar(er)
