2022-05-24 13:17:24,792 [INFO] root: Registry: ['nvcr.io'] 2022-05-24 13:17:24,869 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.21.11-tf1.15.5-py3 2022-05-24 13:17:24,965 [WARNING] tlt.components.docker_handler.docker_handler: Docker will run the commands as root. If you would like to retain your local host permissions, please add the "user":"UID:GID" in the DockerOptions portion of the "/home/ataka/.tao_mounts.json" file. You can obtain your users UID and GID by using the "id -u" and "id -g" commands on the terminal. Using TensorFlow backend. WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them. Using TensorFlow backend. /usr/local/lib/python3.6/dist-packages/numba/cuda/envvars.py:17: NumbaWarning: Environment variables with the 'NUMBAPRO' prefix are deprecated and consequently ignored, found use of NUMBAPRO_NVVM=/usr/local/cuda/nvvm/lib64/libnvvm.so. For more information about alternatives visit: ('http://numba.pydata.org/numba-doc/latest/cuda/overview.html', '#cudatoolkit-lookup') warnings.warn(errors.NumbaWarning(msg)) /usr/local/lib/python3.6/dist-packages/numba/cuda/envvars.py:17: NumbaWarning: Environment variables with the 'NUMBAPRO' prefix are deprecated and consequently ignored, found use of NUMBAPRO_LIBDEVICE=/usr/local/cuda/nvvm/libdevice/. For more information about alternatives visit: ('http://numba.pydata.org/numba-doc/latest/cuda/overview.html', '#cudatoolkit-lookup') warnings.warn(errors.NumbaWarning(msg)) 2022-05-24 04:17:32,048 [INFO] iva.unet.spec_handler.spec_loader: Merging specification from /workspace/tao-experiments/unet/specs/unet_train_resnet_unet_kitti_retrain.txt 2022-05-24 04:17:32,055 [INFO] iva.unet.model.utilities: Label Id 0: Train Id 0 2022-05-24 04:17:32,055 [INFO] iva.unet.model.utilities: Label Id 1: Train Id 1 2022-05-24 04:17:32,055 [INFO] iva.unet.model.utilities: Label Id 2: Train Id 2 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 3: Train Id 3 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 4: Train Id 4 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 5: Train Id 5 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 6: Train Id 6 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 7: Train Id 7 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 8: Train Id 8 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 9: Train Id 9 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 10: Train Id 10 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 11: Train Id 11 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 12: Train Id 12 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 13: Train Id 13 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 14: Train Id 14 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 15: Train Id 15 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 16: Train Id 16 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 17: Train Id 17 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 18: Train Id 18 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 19: Train Id 19 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 20: Train Id 20 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 21: Train Id 21 2022-05-24 04:17:32,056 [INFO] iva.unet.model.utilities: Label Id 22: Train Id 22 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 23: Train Id 23 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 24: Train Id 24 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 25: Train Id 25 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 26: Train Id 26 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 27: Train Id 27 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 28: Train Id 28 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 29: Train Id 29 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 30: Train Id 30 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 31: Train Id 31 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 32: Train Id 32 2022-05-24 04:17:32,057 [INFO] iva.unet.model.utilities: Label Id 33: Train Id 33 2022-05-24 04:17:32,057 [INFO] iva.unet.model.model_io: Loading weights from /workspace/tao-experiments/unet/kitti_experiment_retrain/weights/model_kitti_retrained.tlt __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== input_1 (InputLayer) (None, 3, 320, 320) 0 __________________________________________________________________________________________________ conv1 (Conv2D) (None, 64, 160, 160) 9472 input_1[0][0] __________________________________________________________________________________________________ activation_1 (Activation) (None, 64, 160, 160) 0 conv1[0][0] __________________________________________________________________________________________________ block_1a_conv_1 (Conv2D) (None, 64, 80, 80) 36928 activation_1[0][0] __________________________________________________________________________________________________ block_1a_relu_1 (Activation) (None, 64, 80, 80) 0 block_1a_conv_1[0][0] __________________________________________________________________________________________________ block_1a_conv_2 (Conv2D) (None, 64, 80, 80) 36928 block_1a_relu_1[0][0] __________________________________________________________________________________________________ block_1a_conv_shortcut (Conv2D) (None, 64, 80, 80) 4160 activation_1[0][0] __________________________________________________________________________________________________ add_1 (Add) (None, 64, 80, 80) 0 block_1a_conv_2[0][0] block_1a_conv_shortcut[0][0] __________________________________________________________________________________________________ block_1a_relu (Activation) (None, 64, 80, 80) 0 add_1[0][0] __________________________________________________________________________________________________ block_1b_conv_1 (Conv2D) (None, 64, 80, 80) 36928 block_1a_relu[0][0] __________________________________________________________________________________________________ block_1b_relu_1 (Activation) (None, 64, 80, 80) 0 block_1b_conv_1[0][0] __________________________________________________________________________________________________ block_1b_conv_2 (Conv2D) (None, 64, 80, 80) 36928 block_1b_relu_1[0][0] __________________________________________________________________________________________________ block_1b_conv_shortcut (Conv2D) (None, 64, 80, 80) 4160 block_1a_relu[0][0] __________________________________________________________________________________________________ add_2 (Add) (None, 64, 80, 80) 0 block_1b_conv_2[0][0] block_1b_conv_shortcut[0][0] __________________________________________________________________________________________________ block_1b_relu (Activation) (None, 64, 80, 80) 0 add_2[0][0] __________________________________________________________________________________________________ block_2a_conv_1 (Conv2D) (None, 120, 40, 40) 69240 block_1b_relu[0][0] __________________________________________________________________________________________________ block_2a_relu_1 (Activation) (None, 120, 40, 40) 0 block_2a_conv_1[0][0] __________________________________________________________________________________________________ block_2a_conv_2 (Conv2D) (None, 128, 40, 40) 138368 block_2a_relu_1[0][0] __________________________________________________________________________________________________ block_2a_conv_shortcut (Conv2D) (None, 128, 40, 40) 8320 block_1b_relu[0][0] __________________________________________________________________________________________________ add_3 (Add) (None, 128, 40, 40) 0 block_2a_conv_2[0][0] block_2a_conv_shortcut[0][0] __________________________________________________________________________________________________ block_2a_relu (Activation) (None, 128, 40, 40) 0 add_3[0][0] __________________________________________________________________________________________________ block_2b_conv_1 (Conv2D) (None, 120, 40, 40) 138360 block_2a_relu[0][0] __________________________________________________________________________________________________ block_2b_relu_1 (Activation) (None, 120, 40, 40) 0 block_2b_conv_1[0][0] __________________________________________________________________________________________________ block_2b_conv_2 (Conv2D) (None, 112, 40, 40) 121072 block_2b_relu_1[0][0] __________________________________________________________________________________________________ block_2b_conv_shortcut (Conv2D) (None, 112, 40, 40) 14448 block_2a_relu[0][0] __________________________________________________________________________________________________ add_4 (Add) (None, 112, 40, 40) 0 block_2b_conv_2[0][0] block_2b_conv_shortcut[0][0] __________________________________________________________________________________________________ block_2b_relu (Activation) (None, 112, 40, 40) 0 add_4[0][0] __________________________________________________________________________________________________ block_3a_conv_1 (Conv2D) (None, 208, 20, 20) 209872 block_2b_relu[0][0] __________________________________________________________________________________________________ block_3a_relu_1 (Activation) (None, 208, 20, 20) 0 block_3a_conv_1[0][0] __________________________________________________________________________________________________ block_3a_conv_2 (Conv2D) (None, 224, 20, 20) 419552 block_3a_relu_1[0][0] __________________________________________________________________________________________________ block_3a_conv_shortcut (Conv2D) (None, 224, 20, 20) 25312 block_2b_relu[0][0] __________________________________________________________________________________________________ add_5 (Add) (None, 224, 20, 20) 0 block_3a_conv_2[0][0] block_3a_conv_shortcut[0][0] __________________________________________________________________________________________________ block_3a_relu (Activation) (None, 224, 20, 20) 0 add_5[0][0] __________________________________________________________________________________________________ block_3b_conv_1 (Conv2D) (None, 216, 20, 20) 435672 block_3a_relu[0][0] __________________________________________________________________________________________________ block_3b_relu_1 (Activation) (None, 216, 20, 20) 0 block_3b_conv_1[0][0] __________________________________________________________________________________________________ block_3b_conv_2 (Conv2D) (None, 216, 20, 20) 420120 block_3b_relu_1[0][0] __________________________________________________________________________________________________ block_3b_conv_shortcut (Conv2D) (None, 216, 20, 20) 48600 block_3a_relu[0][0] __________________________________________________________________________________________________ add_6 (Add) (None, 216, 20, 20) 0 block_3b_conv_2[0][0] block_3b_conv_shortcut[0][0] __________________________________________________________________________________________________ block_3b_relu (Activation) (None, 216, 20, 20) 0 add_6[0][0] __________________________________________________________________________________________________ block_4a_conv_1 (Conv2D) (None, 416, 20, 20) 809120 block_3b_relu[0][0] __________________________________________________________________________________________________ block_4a_relu_1 (Activation) (None, 416, 20, 20) 0 block_4a_conv_1[0][0] __________________________________________________________________________________________________ block_4a_conv_2 (Conv2D) (None, 392, 20, 20) 1468040 block_4a_relu_1[0][0] __________________________________________________________________________________________________ block_4a_conv_shortcut (Conv2D) (None, 392, 20, 20) 85064 block_3b_relu[0][0] __________________________________________________________________________________________________ add_7 (Add) (None, 392, 20, 20) 0 block_4a_conv_2[0][0] block_4a_conv_shortcut[0][0] __________________________________________________________________________________________________ block_4a_relu (Activation) (None, 392, 20, 20) 0 add_7[0][0] __________________________________________________________________________________________________ block_4b_conv_1 (Conv2D) (None, 384, 20, 20) 1355136 block_4a_relu[0][0] __________________________________________________________________________________________________ block_4b_relu_1 (Activation) (None, 384, 20, 20) 0 block_4b_conv_1[0][0] __________________________________________________________________________________________________ block_4b_conv_2 (Conv2D) (None, 424, 20, 20) 1465768 block_4b_relu_1[0][0] __________________________________________________________________________________________________ block_4b_conv_shortcut (Conv2D) (None, 424, 20, 20) 166632 block_4a_relu[0][0] __________________________________________________________________________________________________ add_8 (Add) (None, 424, 20, 20) 0 block_4b_conv_2[0][0] block_4b_conv_shortcut[0][0] __________________________________________________________________________________________________ block_4b_relu (Activation) (None, 424, 20, 20) 0 add_8[0][0] __________________________________________________________________________________________________ conv2d_transpose_1 (Conv2DTrans (None, 256, 40, 40) 1736960 block_4b_relu[0][0] __________________________________________________________________________________________________ concatenate_1 (Concatenate) (None, 368, 40, 40) 0 conv2d_transpose_1[0][0] block_2b_relu[0][0] __________________________________________________________________________________________________ activation_2 (Activation) (None, 368, 40, 40) 0 concatenate_1[0][0] __________________________________________________________________________________________________ conv2d_1 (Conv2D) (None, 256, 40, 40) 848128 activation_2[0][0] __________________________________________________________________________________________________ activation_3 (Activation) (None, 256, 40, 40) 0 conv2d_1[0][0] __________________________________________________________________________________________________ conv2d_transpose_2 (Conv2DTrans (None, 128, 80, 80) 524416 activation_3[0][0] __________________________________________________________________________________________________ concatenate_2 (Concatenate) (None, 192, 80, 80) 0 conv2d_transpose_2[0][0] block_1b_relu[0][0] __________________________________________________________________________________________________ activation_4 (Activation) (None, 192, 80, 80) 0 concatenate_2[0][0] __________________________________________________________________________________________________ conv2d_2 (Conv2D) (None, 128, 80, 80) 221312 activation_4[0][0] __________________________________________________________________________________________________ activation_5 (Activation) (None, 128, 80, 80) 0 conv2d_2[0][0] __________________________________________________________________________________________________ conv2d_transpose_3 (Conv2DTrans (None, 64, 160, 160) 131136 activation_5[0][0] __________________________________________________________________________________________________ concatenate_3 (Concatenate) (None, 128, 160, 160 0 conv2d_transpose_3[0][0] activation_1[0][0] __________________________________________________________________________________________________ activation_6 (Activation) (None, 128, 160, 160 0 concatenate_3[0][0] __________________________________________________________________________________________________ conv2d_3 (Conv2D) (None, 64, 160, 160) 73792 activation_6[0][0] __________________________________________________________________________________________________ activation_7 (Activation) (None, 64, 160, 160) 0 conv2d_3[0][0] __________________________________________________________________________________________________ conv2d_transpose_4 (Conv2DTrans (None, 64, 320, 320) 65600 activation_7[0][0] __________________________________________________________________________________________________ activation_8 (Activation) (None, 64, 320, 320) 0 conv2d_transpose_4[0][0] __________________________________________________________________________________________________ conv2d_4 (Conv2D) (None, 64, 320, 320) 36928 activation_8[0][0] __________________________________________________________________________________________________ activation_9 (Activation) (None, 64, 320, 320) 0 conv2d_4[0][0] __________________________________________________________________________________________________ conv2d_5 (Conv2D) (None, 34, 320, 320) 19618 activation_9[0][0] __________________________________________________________________________________________________ permute_1 (Permute) (None, 320, 320, 34) 0 conv2d_5[0][0] __________________________________________________________________________________________________ softmax_1 (Softmax) (None, 320, 320, 34) 0 permute_1[0][0] ================================================================================================== Total params: 11,222,090 Trainable params: 11,222,090 Non-trainable params: 0 __________________________________________________________________________________________________ 2022-05-24 04:17:35,725 [INFO] iva.unet.model.model_io: Loaded weights Successfully for Export 2022-05-24 04:17:35,725 [INFO] root: Using input nodes: ['input_1'] 2022-05-24 04:17:35,725 [INFO] root: Using output nodes: ['softmax_1'] 2022-05-24 04:17:35,726 [INFO] iva.common.export.keras_exporter: Using input nodes: ['input_1'] 2022-05-24 04:17:35,726 [INFO] iva.common.export.keras_exporter: Using output nodes: ['softmax_1'] The ONNX operator number change on the optimization: 144 -> 72 2022-05-24 04:17:40,129 [INFO] keras2onnx: The ONNX operator number change on the optimization: 144 -> 72 2022-05-24 04:17:40,420 [WARNING] onnxmltools: The maximum opset needed by this model is only 11. 2022-05-24 04:17:41,048 [INFO] numba.cuda.cudadrv.driver: init 2022-05-24 04:17:41,191 [INFO] iva.unet.export.unet_exporter: Converted model was saved into /workspace/tao-experiments/unet/kitti_experiment_retrain/weights/model_kitti_retrained.etlt 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 0: Train Id 0 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 1: Train Id 1 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 2: Train Id 2 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 3: Train Id 3 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 4: Train Id 4 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 5: Train Id 5 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 6: Train Id 6 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 7: Train Id 7 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 8: Train Id 8 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 9: Train Id 9 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 10: Train Id 10 2022-05-24 04:17:41,203 [INFO] iva.unet.model.utilities: Label Id 11: Train Id 11 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 12: Train Id 12 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 13: Train Id 13 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 14: Train Id 14 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 15: Train Id 15 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 16: Train Id 16 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 17: Train Id 17 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 18: Train Id 18 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 19: Train Id 19 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 20: Train Id 20 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 21: Train Id 21 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 22: Train Id 22 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 23: Train Id 23 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 24: Train Id 24 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 25: Train Id 25 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 26: Train Id 26 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 27: Train Id 27 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 28: Train Id 28 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 29: Train Id 29 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 30: Train Id 30 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 31: Train Id 31 2022-05-24 04:17:41,204 [INFO] iva.unet.model.utilities: Label Id 32: Train Id 32 2022-05-24 04:17:41,205 [INFO] iva.unet.model.utilities: Label Id 33: Train Id 33 2022-05-24 04:17:58,405 [INFO] root: Export complete. 2022-05-24 04:17:58,406 [INFO] root: { "param_count": 11.22209, "size": 99.92537879943848 } 2022-05-24 13:17:59,775 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.