Using TensorFlow backend. WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them. Using TensorFlow backend. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/horovod/tensorflow/__init__.py:117: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead. 2021-05-05 07:44:02,658 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/horovod/tensorflow/__init__.py:117: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/horovod/tensorflow/__init__.py:143: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead. 2021-05-05 07:44:02,659 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/horovod/tensorflow/__init__.py:143: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead. WARNING:tensorflow:From /home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/yolo_v4/scripts/train.py:49: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead. 2021-05-05 07:44:02,723 [WARNING] tensorflow: From /home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/yolo_v4/scripts/train.py:49: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead. WARNING:tensorflow:From /home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/yolo_v4/scripts/train.py:52: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead. 2021-05-05 07:44:02,724 [WARNING] tensorflow: From /home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/yolo_v4/scripts/train.py:52: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead. 2021-05-05 07:44:03,192 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead. 2021-05-05 07:44:03,194 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1834: The name tf.nn.fused_batch_norm is deprecated. Please use tf.compat.v1.nn.fused_batch_norm instead. 2021-05-05 07:44:03,217 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:1834: The name tf.nn.fused_batch_norm is deprecated. Please use tf.compat.v1.nn.fused_batch_norm instead. WARNING:tensorflow:From /opt/nvidia/third_party/keras/tensorflow_backend.py:183: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead. 2021-05-05 07:44:03,883 [WARNING] tensorflow: From /opt/nvidia/third_party/keras/tensorflow_backend.py:183: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:2018: The name tf.image.resize_nearest_neighbor is deprecated. Please use tf.compat.v1.image.resize_nearest_neighbor instead. 2021-05-05 07:44:04,143 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:2018: The name tf.image.resize_nearest_neighbor is deprecated. Please use tf.compat.v1.image.resize_nearest_neighbor instead. WARNING:tensorflow:From /opt/nvidia/third_party/keras/tensorflow_backend.py:187: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead. 2021-05-05 07:44:06,545 [WARNING] tensorflow: From /opt/nvidia/third_party/keras/tensorflow_backend.py:187: The name tf.nn.avg_pool is deprecated. Please use tf.nn.avg_pool2d instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead. 2021-05-05 07:44:06,768 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:199: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead. 2021-05-05 07:44:06,769 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:199: The name tf.is_variable_initialized is deprecated. Please use tf.compat.v1.is_variable_initialized instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:206: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead. 2021-05-05 07:44:07,570 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:206: The name tf.variables_initializer is deprecated. Please use tf.compat.v1.variables_initializer instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead. 2021-05-05 07:44:08,508 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3295: The name tf.log is deprecated. Please use tf.math.log instead. 2021-05-05 07:44:08,512 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:3295: The name tf.log is deprecated. Please use tf.math.log instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead. 2021-05-05 07:44:09,252 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead. WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:973: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead. 2021-05-05 07:44:09,430 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:973: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead. __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== Input (InputLayer) (None, 3, 384, 1248) 0 __________________________________________________________________________________________________ conv1 (Conv2D) (None, 64, 192, 624) 9408 Input[0][0] __________________________________________________________________________________________________ bn_conv1 (BatchNormalization) (None, 64, 192, 624) 256 conv1[0][0] __________________________________________________________________________________________________ activation_2 (Activation) (None, 64, 192, 624) 0 bn_conv1[0][0] __________________________________________________________________________________________________ block_1a_conv_1 (Conv2D) (None, 64, 96, 312) 36864 activation_2[0][0] __________________________________________________________________________________________________ block_1a_bn_1 (BatchNormalizati (None, 64, 96, 312) 256 block_1a_conv_1[0][0] __________________________________________________________________________________________________ block_1a_relu_1 (Activation) (None, 64, 96, 312) 0 block_1a_bn_1[0][0] __________________________________________________________________________________________________ block_1a_conv_2 (Conv2D) (None, 64, 96, 312) 36864 block_1a_relu_1[0][0] __________________________________________________________________________________________________ block_1a_conv_shortcut (Conv2D) (None, 64, 96, 312) 4096 activation_2[0][0] __________________________________________________________________________________________________ block_1a_bn_2 (BatchNormalizati (None, 64, 96, 312) 256 block_1a_conv_2[0][0] __________________________________________________________________________________________________ block_1a_bn_shortcut (BatchNorm (None, 64, 96, 312) 256 block_1a_conv_shortcut[0][0] __________________________________________________________________________________________________ add_9 (Add) (None, 64, 96, 312) 0 block_1a_bn_2[0][0] block_1a_bn_shortcut[0][0] __________________________________________________________________________________________________ block_1a_relu (Activation) (None, 64, 96, 312) 0 add_9[0][0] __________________________________________________________________________________________________ block_1b_conv_1 (Conv2D) (None, 64, 96, 312) 36864 block_1a_relu[0][0] __________________________________________________________________________________________________ block_1b_bn_1 (BatchNormalizati (None, 64, 96, 312) 256 block_1b_conv_1[0][0] __________________________________________________________________________________________________ block_1b_relu_1 (Activation) (None, 64, 96, 312) 0 block_1b_bn_1[0][0] __________________________________________________________________________________________________ block_1b_conv_2 (Conv2D) (None, 64, 96, 312) 36864 block_1b_relu_1[0][0] __________________________________________________________________________________________________ block_1b_conv_shortcut (Conv2D) (None, 64, 96, 312) 4096 block_1a_relu[0][0] __________________________________________________________________________________________________ block_1b_bn_2 (BatchNormalizati (None, 64, 96, 312) 256 block_1b_conv_2[0][0] __________________________________________________________________________________________________ block_1b_bn_shortcut (BatchNorm (None, 64, 96, 312) 256 block_1b_conv_shortcut[0][0] __________________________________________________________________________________________________ add_10 (Add) (None, 64, 96, 312) 0 block_1b_bn_2[0][0] block_1b_bn_shortcut[0][0] __________________________________________________________________________________________________ block_1b_relu (Activation) (None, 64, 96, 312) 0 add_10[0][0] __________________________________________________________________________________________________ block_2a_conv_1 (Conv2D) (None, 128, 48, 156) 73728 block_1b_relu[0][0] __________________________________________________________________________________________________ block_2a_bn_1 (BatchNormalizati (None, 128, 48, 156) 512 block_2a_conv_1[0][0] __________________________________________________________________________________________________ block_2a_relu_1 (Activation) (None, 128, 48, 156) 0 block_2a_bn_1[0][0] __________________________________________________________________________________________________ block_2a_conv_2 (Conv2D) (None, 128, 48, 156) 147456 block_2a_relu_1[0][0] __________________________________________________________________________________________________ block_2a_conv_shortcut (Conv2D) (None, 128, 48, 156) 8192 block_1b_relu[0][0] __________________________________________________________________________________________________ block_2a_bn_2 (BatchNormalizati (None, 128, 48, 156) 512 block_2a_conv_2[0][0] __________________________________________________________________________________________________ block_2a_bn_shortcut (BatchNorm (None, 128, 48, 156) 512 block_2a_conv_shortcut[0][0] __________________________________________________________________________________________________ add_11 (Add) (None, 128, 48, 156) 0 block_2a_bn_2[0][0] block_2a_bn_shortcut[0][0] __________________________________________________________________________________________________ block_2a_relu (Activation) (None, 128, 48, 156) 0 add_11[0][0] __________________________________________________________________________________________________ block_2b_conv_1 (Conv2D) (None, 128, 48, 156) 147456 block_2a_relu[0][0] __________________________________________________________________________________________________ block_2b_bn_1 (BatchNormalizati (None, 128, 48, 156) 512 block_2b_conv_1[0][0] __________________________________________________________________________________________________ block_2b_relu_1 (Activation) (None, 128, 48, 156) 0 block_2b_bn_1[0][0] __________________________________________________________________________________________________ block_2b_conv_2 (Conv2D) (None, 128, 48, 156) 147456 block_2b_relu_1[0][0] __________________________________________________________________________________________________ block_2b_conv_shortcut (Conv2D) (None, 128, 48, 156) 16384 block_2a_relu[0][0] __________________________________________________________________________________________________ block_2b_bn_2 (BatchNormalizati (None, 128, 48, 156) 512 block_2b_conv_2[0][0] __________________________________________________________________________________________________ block_2b_bn_shortcut (BatchNorm (None, 128, 48, 156) 512 block_2b_conv_shortcut[0][0] __________________________________________________________________________________________________ add_12 (Add) (None, 128, 48, 156) 0 block_2b_bn_2[0][0] block_2b_bn_shortcut[0][0] __________________________________________________________________________________________________ block_2b_relu (Activation) (None, 128, 48, 156) 0 add_12[0][0] __________________________________________________________________________________________________ block_3a_conv_1 (Conv2D) (None, 256, 24, 78) 294912 block_2b_relu[0][0] __________________________________________________________________________________________________ block_3a_bn_1 (BatchNormalizati (None, 256, 24, 78) 1024 block_3a_conv_1[0][0] __________________________________________________________________________________________________ block_3a_relu_1 (Activation) (None, 256, 24, 78) 0 block_3a_bn_1[0][0] __________________________________________________________________________________________________ block_3a_conv_2 (Conv2D) (None, 256, 24, 78) 589824 block_3a_relu_1[0][0] __________________________________________________________________________________________________ block_3a_conv_shortcut (Conv2D) (None, 256, 24, 78) 32768 block_2b_relu[0][0] __________________________________________________________________________________________________ block_3a_bn_2 (BatchNormalizati (None, 256, 24, 78) 1024 block_3a_conv_2[0][0] __________________________________________________________________________________________________ block_3a_bn_shortcut (BatchNorm (None, 256, 24, 78) 1024 block_3a_conv_shortcut[0][0] __________________________________________________________________________________________________ add_13 (Add) (None, 256, 24, 78) 0 block_3a_bn_2[0][0] block_3a_bn_shortcut[0][0] __________________________________________________________________________________________________ block_3a_relu (Activation) (None, 256, 24, 78) 0 add_13[0][0] __________________________________________________________________________________________________ block_3b_conv_1 (Conv2D) (None, 256, 24, 78) 589824 block_3a_relu[0][0] __________________________________________________________________________________________________ block_3b_bn_1 (BatchNormalizati (None, 256, 24, 78) 1024 block_3b_conv_1[0][0] __________________________________________________________________________________________________ block_3b_relu_1 (Activation) (None, 256, 24, 78) 0 block_3b_bn_1[0][0] __________________________________________________________________________________________________ block_3b_conv_2 (Conv2D) (None, 256, 24, 78) 589824 block_3b_relu_1[0][0] __________________________________________________________________________________________________ block_3b_conv_shortcut (Conv2D) (None, 256, 24, 78) 65536 block_3a_relu[0][0] __________________________________________________________________________________________________ block_3b_bn_2 (BatchNormalizati (None, 256, 24, 78) 1024 block_3b_conv_2[0][0] __________________________________________________________________________________________________ block_3b_bn_shortcut (BatchNorm (None, 256, 24, 78) 1024 block_3b_conv_shortcut[0][0] __________________________________________________________________________________________________ add_14 (Add) (None, 256, 24, 78) 0 block_3b_bn_2[0][0] block_3b_bn_shortcut[0][0] __________________________________________________________________________________________________ block_3b_relu (Activation) (None, 256, 24, 78) 0 add_14[0][0] __________________________________________________________________________________________________ block_4a_conv_1 (Conv2D) (None, 512, 24, 78) 1179648 block_3b_relu[0][0] __________________________________________________________________________________________________ block_4a_bn_1 (BatchNormalizati (None, 512, 24, 78) 2048 block_4a_conv_1[0][0] __________________________________________________________________________________________________ block_4a_relu_1 (Activation) (None, 512, 24, 78) 0 block_4a_bn_1[0][0] __________________________________________________________________________________________________ block_4a_conv_2 (Conv2D) (None, 512, 24, 78) 2359296 block_4a_relu_1[0][0] __________________________________________________________________________________________________ block_4a_conv_shortcut (Conv2D) (None, 512, 24, 78) 131072 block_3b_relu[0][0] __________________________________________________________________________________________________ block_4a_bn_2 (BatchNormalizati (None, 512, 24, 78) 2048 block_4a_conv_2[0][0] __________________________________________________________________________________________________ block_4a_bn_shortcut (BatchNorm (None, 512, 24, 78) 2048 block_4a_conv_shortcut[0][0] __________________________________________________________________________________________________ add_15 (Add) (None, 512, 24, 78) 0 block_4a_bn_2[0][0] block_4a_bn_shortcut[0][0] __________________________________________________________________________________________________ block_4a_relu (Activation) (None, 512, 24, 78) 0 add_15[0][0] __________________________________________________________________________________________________ block_4b_conv_1 (Conv2D) (None, 512, 24, 78) 2359296 block_4a_relu[0][0] __________________________________________________________________________________________________ block_4b_bn_1 (BatchNormalizati (None, 512, 24, 78) 2048 block_4b_conv_1[0][0] __________________________________________________________________________________________________ block_4b_relu_1 (Activation) (None, 512, 24, 78) 0 block_4b_bn_1[0][0] __________________________________________________________________________________________________ block_4b_conv_2 (Conv2D) (None, 512, 24, 78) 2359296 block_4b_relu_1[0][0] __________________________________________________________________________________________________ block_4b_conv_shortcut (Conv2D) (None, 512, 24, 78) 262144 block_4a_relu[0][0] __________________________________________________________________________________________________ block_4b_bn_2 (BatchNormalizati (None, 512, 24, 78) 2048 block_4b_conv_2[0][0] __________________________________________________________________________________________________ block_4b_bn_shortcut (BatchNorm (None, 512, 24, 78) 2048 block_4b_conv_shortcut[0][0] __________________________________________________________________________________________________ add_16 (Add) (None, 512, 24, 78) 0 block_4b_bn_2[0][0] block_4b_bn_shortcut[0][0] __________________________________________________________________________________________________ block_4b_relu (Activation) (None, 512, 24, 78) 0 add_16[0][0] __________________________________________________________________________________________________ yolo_spp_pool_1 (MaxPooling2D) (None, 512, 24, 78) 0 block_4b_relu[0][0] __________________________________________________________________________________________________ yolo_spp_pool_2 (MaxPooling2D) (None, 512, 24, 78) 0 block_4b_relu[0][0] __________________________________________________________________________________________________ yolo_spp_pool_3 (MaxPooling2D) (None, 512, 24, 78) 0 block_4b_relu[0][0] __________________________________________________________________________________________________ yolo_spp_concat (Concatenate) (None, 2048, 24, 78) 0 yolo_spp_pool_1[0][0] yolo_spp_pool_2[0][0] yolo_spp_pool_3[0][0] block_4b_relu[0][0] __________________________________________________________________________________________________ yolo_spp_conv (Conv2D) (None, 512, 24, 78) 1048576 yolo_spp_concat[0][0] __________________________________________________________________________________________________ yolo_spp_conv_bn (BatchNormaliz (None, 512, 24, 78) 2048 yolo_spp_conv[0][0] __________________________________________________________________________________________________ yolo_spp_conv_lrelu (LeakyReLU) (None, 512, 24, 78) 0 yolo_spp_conv_bn[0][0] __________________________________________________________________________________________________ yolo_expand_conv1 (Conv2D) (None, 512, 12, 39) 2359296 yolo_spp_conv_lrelu[0][0] __________________________________________________________________________________________________ yolo_expand_conv1_bn (BatchNorm (None, 512, 12, 39) 2048 yolo_expand_conv1[0][0] __________________________________________________________________________________________________ yolo_expand_conv1_lrelu (LeakyR (None, 512, 12, 39) 0 yolo_expand_conv1_bn[0][0] __________________________________________________________________________________________________ yolo_conv1_1 (Conv2D) (None, 256, 12, 39) 131072 yolo_expand_conv1_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv1_1_bn (BatchNormaliza (None, 256, 12, 39) 1024 yolo_conv1_1[0][0] __________________________________________________________________________________________________ yolo_conv1_1_lrelu (LeakyReLU) (None, 256, 12, 39) 0 yolo_conv1_1_bn[0][0] __________________________________________________________________________________________________ yolo_conv1_2 (Conv2D) (None, 512, 12, 39) 1179648 yolo_conv1_1_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv1_2_bn (BatchNormaliza (None, 512, 12, 39) 2048 yolo_conv1_2[0][0] __________________________________________________________________________________________________ yolo_conv1_2_lrelu (LeakyReLU) (None, 512, 12, 39) 0 yolo_conv1_2_bn[0][0] __________________________________________________________________________________________________ yolo_conv1_3 (Conv2D) (None, 256, 12, 39) 131072 yolo_conv1_2_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv1_3_bn (BatchNormaliza (None, 256, 12, 39) 1024 yolo_conv1_3[0][0] __________________________________________________________________________________________________ yolo_conv1_3_lrelu (LeakyReLU) (None, 256, 12, 39) 0 yolo_conv1_3_bn[0][0] __________________________________________________________________________________________________ yolo_conv1_4 (Conv2D) (None, 512, 12, 39) 1179648 yolo_conv1_3_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv1_4_bn (BatchNormaliza (None, 512, 12, 39) 2048 yolo_conv1_4[0][0] __________________________________________________________________________________________________ yolo_conv1_4_lrelu (LeakyReLU) (None, 512, 12, 39) 0 yolo_conv1_4_bn[0][0] __________________________________________________________________________________________________ yolo_conv1_5 (Conv2D) (None, 256, 12, 39) 131072 yolo_conv1_4_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv1_5_bn (BatchNormaliza (None, 256, 12, 39) 1024 yolo_conv1_5[0][0] __________________________________________________________________________________________________ yolo_conv1_5_lrelu (LeakyReLU) (None, 256, 12, 39) 0 yolo_conv1_5_bn[0][0] __________________________________________________________________________________________________ yolo_conv2 (Conv2D) (None, 128, 12, 39) 32768 yolo_conv1_5_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv2_bn (BatchNormalizati (None, 128, 12, 39) 512 yolo_conv2[0][0] __________________________________________________________________________________________________ yolo_conv2_lrelu (LeakyReLU) (None, 128, 12, 39) 0 yolo_conv2_bn[0][0] __________________________________________________________________________________________________ upsample0 (UpSampling2D) (None, 128, 24, 78) 0 yolo_conv2_lrelu[0][0] __________________________________________________________________________________________________ concatenate_3 (Concatenate) (None, 384, 24, 78) 0 upsample0[0][0] block_3b_relu[0][0] __________________________________________________________________________________________________ yolo_conv3_1 (Conv2D) (None, 128, 24, 78) 49152 concatenate_3[0][0] __________________________________________________________________________________________________ yolo_conv3_1_bn (BatchNormaliza (None, 128, 24, 78) 512 yolo_conv3_1[0][0] __________________________________________________________________________________________________ yolo_conv3_1_lrelu (LeakyReLU) (None, 128, 24, 78) 0 yolo_conv3_1_bn[0][0] __________________________________________________________________________________________________ yolo_conv3_2 (Conv2D) (None, 256, 24, 78) 294912 yolo_conv3_1_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv3_2_bn (BatchNormaliza (None, 256, 24, 78) 1024 yolo_conv3_2[0][0] __________________________________________________________________________________________________ yolo_conv3_2_lrelu (LeakyReLU) (None, 256, 24, 78) 0 yolo_conv3_2_bn[0][0] __________________________________________________________________________________________________ yolo_conv3_3 (Conv2D) (None, 128, 24, 78) 32768 yolo_conv3_2_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv3_3_bn (BatchNormaliza (None, 128, 24, 78) 512 yolo_conv3_3[0][0] __________________________________________________________________________________________________ yolo_conv3_3_lrelu (LeakyReLU) (None, 128, 24, 78) 0 yolo_conv3_3_bn[0][0] __________________________________________________________________________________________________ yolo_conv3_4 (Conv2D) (None, 256, 24, 78) 294912 yolo_conv3_3_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv3_4_bn (BatchNormaliza (None, 256, 24, 78) 1024 yolo_conv3_4[0][0] __________________________________________________________________________________________________ yolo_conv3_4_lrelu (LeakyReLU) (None, 256, 24, 78) 0 yolo_conv3_4_bn[0][0] __________________________________________________________________________________________________ yolo_conv3_5 (Conv2D) (None, 128, 24, 78) 32768 yolo_conv3_4_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv3_5_bn (BatchNormaliza (None, 128, 24, 78) 512 yolo_conv3_5[0][0] __________________________________________________________________________________________________ yolo_conv3_5_lrelu (LeakyReLU) (None, 128, 24, 78) 0 yolo_conv3_5_bn[0][0] __________________________________________________________________________________________________ yolo_conv4 (Conv2D) (None, 64, 24, 78) 8192 yolo_conv3_5_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv4_bn (BatchNormalizati (None, 64, 24, 78) 256 yolo_conv4[0][0] __________________________________________________________________________________________________ yolo_conv4_lrelu (LeakyReLU) (None, 64, 24, 78) 0 yolo_conv4_bn[0][0] __________________________________________________________________________________________________ upsample1 (UpSampling2D) (None, 64, 48, 156) 0 yolo_conv4_lrelu[0][0] __________________________________________________________________________________________________ concatenate_4 (Concatenate) (None, 192, 48, 156) 0 upsample1[0][0] block_2b_relu[0][0] __________________________________________________________________________________________________ yolo_conv5_1 (Conv2D) (None, 64, 48, 156) 12288 concatenate_4[0][0] __________________________________________________________________________________________________ yolo_conv5_1_bn (BatchNormaliza (None, 64, 48, 156) 256 yolo_conv5_1[0][0] __________________________________________________________________________________________________ yolo_conv5_1_lrelu (LeakyReLU) (None, 64, 48, 156) 0 yolo_conv5_1_bn[0][0] __________________________________________________________________________________________________ yolo_conv5_2 (Conv2D) (None, 128, 48, 156) 73728 yolo_conv5_1_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv5_2_bn (BatchNormaliza (None, 128, 48, 156) 512 yolo_conv5_2[0][0] __________________________________________________________________________________________________ yolo_conv5_2_lrelu (LeakyReLU) (None, 128, 48, 156) 0 yolo_conv5_2_bn[0][0] __________________________________________________________________________________________________ yolo_conv5_3 (Conv2D) (None, 64, 48, 156) 8192 yolo_conv5_2_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv5_3_bn (BatchNormaliza (None, 64, 48, 156) 256 yolo_conv5_3[0][0] __________________________________________________________________________________________________ yolo_conv5_3_lrelu (LeakyReLU) (None, 64, 48, 156) 0 yolo_conv5_3_bn[0][0] __________________________________________________________________________________________________ yolo_conv5_4 (Conv2D) (None, 128, 48, 156) 73728 yolo_conv5_3_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv5_4_bn (BatchNormaliza (None, 128, 48, 156) 512 yolo_conv5_4[0][0] __________________________________________________________________________________________________ yolo_conv5_4_lrelu (LeakyReLU) (None, 128, 48, 156) 0 yolo_conv5_4_bn[0][0] __________________________________________________________________________________________________ yolo_conv5_5 (Conv2D) (None, 64, 48, 156) 8192 yolo_conv5_4_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv5_5_bn (BatchNormaliza (None, 64, 48, 156) 256 yolo_conv5_5[0][0] __________________________________________________________________________________________________ yolo_conv5_5_lrelu (LeakyReLU) (None, 64, 48, 156) 0 yolo_conv5_5_bn[0][0] __________________________________________________________________________________________________ yolo_conv1_6 (Conv2D) (None, 512, 12, 39) 1179648 yolo_conv1_5_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv3_6 (Conv2D) (None, 256, 24, 78) 294912 yolo_conv3_5_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv5_6 (Conv2D) (None, 128, 48, 156) 73728 yolo_conv5_5_lrelu[0][0] __________________________________________________________________________________________________ yolo_conv1_6_bn (BatchNormaliza (None, 512, 12, 39) 2048 yolo_conv1_6[0][0] __________________________________________________________________________________________________ yolo_conv3_6_bn (BatchNormaliza (None, 256, 24, 78) 1024 yolo_conv3_6[0][0] __________________________________________________________________________________________________ yolo_conv5_6_bn (BatchNormaliza (None, 128, 48, 156) 512 yolo_conv5_6[0][0] __________________________________________________________________________________________________ yolo_conv1_6_lrelu (LeakyReLU) (None, 512, 12, 39) 0 yolo_conv1_6_bn[0][0] __________________________________________________________________________________________________ yolo_conv3_6_lrelu (LeakyReLU) (None, 256, 24, 78) 0 yolo_conv3_6_bn[0][0] __________________________________________________________________________________________________ yolo_conv5_6_lrelu (LeakyReLU) (None, 128, 48, 156) 0 yolo_conv5_6_bn[0][0] __________________________________________________________________________________________________ conv_big_object (Conv2D) (None, 15, 12, 39) 7695 yolo_conv1_6_lrelu[0][0] __________________________________________________________________________________________________ conv_mid_object (Conv2D) (None, 15, 24, 78) 3855 yolo_conv3_6_lrelu[0][0] __________________________________________________________________________________________________ conv_sm_object (Conv2D) (None, 15, 48, 156) 1935 yolo_conv5_6_lrelu[0][0] __________________________________________________________________________________________________ bg_permute (Permute) (None, 12, 39, 15) 0 conv_big_object[0][0] __________________________________________________________________________________________________ md_permute (Permute) (None, 24, 78, 15) 0 conv_mid_object[0][0] __________________________________________________________________________________________________ sm_permute (Permute) (None, 48, 156, 15) 0 conv_sm_object[0][0] __________________________________________________________________________________________________ bg_reshape (Reshape) (None, 1404, 5) 0 bg_permute[0][0] __________________________________________________________________________________________________ md_reshape (Reshape) (None, 5616, 5) 0 md_permute[0][0] __________________________________________________________________________________________________ sm_reshape (Reshape) (None, 22464, 5) 0 sm_permute[0][0] __________________________________________________________________________________________________ bg_anchor (YOLOAnchorBox) (None, 1404, 6) 0 conv_big_object[0][0] __________________________________________________________________________________________________ bg_bbox_processor (BBoxPostProc (None, 1404, 5) 0 bg_reshape[0][0] __________________________________________________________________________________________________ md_anchor (YOLOAnchorBox) (None, 5616, 6) 0 conv_mid_object[0][0] __________________________________________________________________________________________________ md_bbox_processor (BBoxPostProc (None, 5616, 5) 0 md_reshape[0][0] __________________________________________________________________________________________________ sm_anchor (YOLOAnchorBox) (None, 22464, 6) 0 conv_sm_object[0][0] __________________________________________________________________________________________________ sm_bbox_processor (BBoxPostProc (None, 22464, 5) 0 sm_reshape[0][0] __________________________________________________________________________________________________ encoded_bg (Concatenate) (None, 1404, 11) 0 bg_anchor[0][0] bg_bbox_processor[0][0] __________________________________________________________________________________________________ encoded_md (Concatenate) (None, 5616, 11) 0 md_anchor[0][0] md_bbox_processor[0][0] __________________________________________________________________________________________________ encoded_sm (Concatenate) (None, 22464, 11) 0 sm_anchor[0][0] sm_bbox_processor[0][0] __________________________________________________________________________________________________ encoded_detections (Concatenate (None, 29484, 11) 0 encoded_bg[0][0] encoded_md[0][0] encoded_sm[0][0] ================================================================================================== Total params: 20,207,213 Trainable params: 20,185,069 Non-trainable params: 22,144 __________________________________________________________________________________________________ 2021-05-05 07:44:39,473 [INFO] __main__: Number of images in the training dataset: 670 Epoch 1/1 1/84 [..............................] - ETA: 34:19 - loss: 83.6538 2/84 [..............................] - ETA: 22:35 - loss: 83.7811/usr/local/lib/python3.6/dist-packages/keras/callbacks.py:122: UserWarning: Method on_batch_end() is slow compared to the batch update (3.924927). Check your callbacks. % delta_t_median)  3/84 [>.............................] - ETA: 15:04 - loss: 83.6885 4/84 [>.............................] - ETA: 11:17 - loss: 83.4971 5/84 [>.............................] - ETA: 9:01 - loss: 83.2646  6/84 [=>............................] - ETA: 7:31 - loss: 83.1176 7/84 [=>............................] - ETA: 6:26 - loss: 82.9791 8/84 [=>............................] - ETA: 5:38 - loss: 82.7630 9/84 [==>...........................] - ETA: 5:00 - loss: 82.5057 10/84 [==>...........................] - ETA: 4:30 - loss: 82.2489 11/84 [==>...........................] - ETA: 4:05 - loss: 81.9396 12/84 [===>..........................] - ETA: 3:44 - loss: 81.7123 13/84 [===>..........................] - ETA: 3:26 - loss: 81.5715 14/84 [====>.........................] - ETA: 3:11 - loss: 81.2515 15/84 [====>.........................] - ETA: 2:58 - loss: 81.0380 16/84 [====>.........................] - ETA: 2:46 - loss: 80.7174 17/84 [=====>........................] - ETA: 2:35 - loss: 80.6314 18/84 [=====>........................] - ETA: 2:26 - loss: 80.2426 19/84 [=====>........................] - ETA: 2:18 - loss: 79.9546 20/84 [======>.......................] - ETA: 2:10 - loss: 79.7579 21/84 [======>.......................] - ETA: 2:03 - loss: 79.3440 22/84 [======>.......................] - ETA: 1:57 - loss: 78.9963 23/84 [=======>......................] - ETA: 1:51 - loss: 78.5509 24/84 [=======>......................] - ETA: 1:46 - loss: 78.3563 25/84 [=======>......................] - ETA: 1:41 - loss: 78.2078 26/84 [========>.....................] - ETA: 1:36 - loss: 77.8169 27/84 [========>.....................] - ETA: 1:32 - loss: 77.3527 28/84 [=========>....................] - ETA: 1:28 - loss: 76.8895 29/84 [=========>....................] - ETA: 1:24 - loss: 76.5392 30/84 [=========>....................] - ETA: 1:30 - loss: 76.0375 31/84 [==========>...................] - ETA: 1:26 - loss: 75.7359 32/84 [==========>...................] - ETA: 1:24 - loss: 75.3855 33/84 [==========>...................] - ETA: 1:21 - loss: 75.1904 34/84 [===========>..................] - ETA: 1:17 - loss: 74.8738 35/84 [===========>..................] - ETA: 1:14 - loss: 74.4618 36/84 [===========>..................] - ETA: 1:11 - loss: 74.1490 37/84 [============>.................] - ETA: 1:11 - loss: 73.8511 38/84 [============>.................] - ETA: 1:11 - loss: 73.6823 39/84 [============>.................] - ETA: 1:09 - loss: 73.2868 40/84 [=============>................] - ETA: 1:06 - loss: 72.9282 41/84 [=============>................] - ETA: 1:04 - loss: 72.6225 42/84 [==============>...............] - ETA: 1:01 - loss: 72.2715 43/84 [==============>...............] - ETA: 59s - loss: 71.8375  44/84 [==============>...............] - ETA: 58s - loss: 71.4375 45/84 [===============>..............] - ETA: 58s - loss: 71.1592 46/84 [===============>..............] - ETA: 55s - loss: 70.8807 47/84 [===============>..............] - ETA: 53s - loss: 70.4707 48/84 [================>.............] - ETA: 51s - loss: 70.1491 49/84 [================>.............] - ETA: 49s - loss: 69.8724 50/84 [================>.............] - ETA: 47s - loss: 69.4845 51/84 [=================>............] - ETA: 47s - loss: 69.2301 52/84 [=================>............] - ETA: 46s - loss: 68.9445 53/84 [=================>............] - ETA: 44s - loss: 68.6912 54/84 [==================>...........] - ETA: 43s - loss: 68.3341 55/84 [==================>...........] - ETA: 41s - loss: 68.0987 56/84 [===================>..........] - ETA: 39s - loss: 67.8006 57/84 [===================>..........] - ETA: 37s - loss: 67.5778 58/84 [===================>..........] - ETA: 36s - loss: 67.2633 59/84 [====================>.........] - ETA: 35s - loss: 66.9713 60/84 [====================>.........] - ETA: 34s - loss: 66.6503 61/84 [====================>.........] - ETA: 32s - loss: 66.5568 62/84 [=====================>........] - ETA: 30s - loss: 66.3452 63/84 [=====================>........] - ETA: 29s - loss: 66.0269 64/84 [=====================>........] - ETA: 27s - loss: 65.7730 65/84 [======================>.......] - ETA: 26s - loss: 65.5553 66/84 [======================>.......] - ETA: 25s - loss: 65.2684 67/84 [======================>.......] - ETA: 23s - loss: 65.0208 68/84 [=======================>......] - ETA: 22s - loss: 64.8165 69/84 [=======================>......] - ETA: 20s - loss: 64.5385 70/84 [========================>.....] - ETA: 19s - loss: 64.3054 71/84 [========================>.....] - ETA: 18s - loss: 64.0641 72/84 [========================>.....] - ETA: 16s - loss: 63.7897 73/84 [=========================>....] - ETA: 15s - loss: 63.5359 74/84 [=========================>....] - ETA: 13s - loss: 63.2882 75/84 [=========================>....] - ETA: 12s - loss: 63.0331 76/84 [==========================>...] - ETA: 11s - loss: 62.7745 77/84 [==========================>...] - ETA: 9s - loss: 62.5305  78/84 [==========================>...] - ETA: 8s - loss: 62.3132 79/84 [===========================>..] - ETA: 6s - loss: 62.1040 80/84 [===========================>..] - ETA: 5s - loss: 61.8671 81/84 [===========================>..] - ETA: 4s - loss: 61.7911 82/84 [============================>.] - ETA: 2s - loss: 61.6327 83/84 [============================>.] - ETA: 1s - loss: 61.4486 84/84 [==============================] - 114s 1s/step - loss: 61.3348 Epoch 00001: saving model to /workspace/tlt-experiments/yolo_v4/experiment_dir_unpruned/weights/yolov4_resnet18_epoch_001.tlt 0% 0/670 [00:00 sys.exit(main()) File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/yolo_v4/entrypoint/yolo_v4.py", line 12, in main File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/common/entrypoint/entrypoint.py", line 296, in launch_job AssertionError: Process run failed.