Using TensorFlow backend. /workspace/miniconda/lib/python3.7/site-packages/skimage/io/manage_plugins.py:23: UserWarning: Your installed pillow version is < 8.1.2. Several security issues (CVE-2021-27921, CVE-2021-25290, CVE-2021-25291, CVE-2021-25293, and more) have been fixed in pillow 8.1.2 or higher. We recommend to upgrade this library. from .collection import imread_collection_wrapper use toolchain binaries WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:245: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-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 /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:181: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:186: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:190: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-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 /workspace/miniconda/lib/python3.7/site-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 /workspace/miniconda/lib/python3.7/site-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 /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:133: The name tf.placeholder_with_default is deprecated. Please use tf.compat.v1.placeholder_with_default instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py:3976: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead. WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-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. /workspace/miniconda/lib/python3.7/site-packages/keras/engine/saving.py:292: UserWarning: No training configuration found in save file: the model was *not* compiled. Compile it manually. warnings.warn('No training configuration found in save file: ' Currently, custom input size is only available for single input size. Mystery node may generate wrong size. running compiler and IP evaluator... Compiler config generated. Compilation and IP Evaluation finished. Npu performance evaluation result: ***** Warning: this model has 1 CPU ops which may cause that the report's fps is different from the actual fps ***** ***** Warning: CPU ops types: KneronResize. [Evaluation Result] estimate FPS float = 21.352 total time = 46.8341 ms total theoretical covolution time = 17.0245 ms average DRAM bandwidth = 0.293015 GB/s MAC efficiency to total time = 36.3507 % MAC idle time = 5.65648 ms MAC running time = 41.1776 ms WARNING:tensorflow:From /workspace/miniconda/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py:1475: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.where in 2.0, which has the same broadcast rule as np.where (array([[258.89148, 470.26517, 297.0268 , 524.3218 ], [233.60538, 218.18251, 306.83316, 381.80396]], dtype=float32), array([0.9251516, 0.787214 ], dtype=float32), array([2, 7], dtype=int32)) processing image: /data1/test_image10/000000001000.jpg processing image: /data1/test_image10/000000001296.jpg processing image: /data1/test_image10/000000005001.jpg processing image: /data1/test_image10/000000000872.jpg processing image: /data1/test_image10/000000001268.jpg processing image: /data1/test_image10/000000000885.jpg processing image: /data1/test_image10/000000000785.jpg processing image: /data1/test_image10/000000000139.jpg processing image: /data1/test_image10/000000005193.jpg processing image: /data1/test_image10/309_190.jpg Success for model "input/input" when running "general/Success" =========================================== = report on flow status = =========================================== kdp520 general knerex gen_nef FPS batch compiler compiler frontend compiler hw info compiler_cfg cpu_node dp analysis buf (KB) dp analysis total (KB) dp_analysis result (KB) Success onnx size (MB) category case input input ✓ ✓ 21 ✓ ✓ ✓ ✓ N/A 21633 21773 140 ✓ 33 Fix point analysis done. Save bie model to '/data1/kneron_flow/input.kdp520.scaled.bie' (array([[259.62997, 472.13394, 294.2162 , 523.1737 ], [234.3568 , 225.17163, 307.17825, 374.8361 ]], dtype=float32), array([0.8921604 , 0.67475265], dtype=float32), array([2, 7], dtype=int32)) [tool][info][batch_compile.cc:513][BatchCompile] compiling input.kdp520.scaled.bie [common][info][compile.cc:62][LoadCfg] Loading config. [piano][info][graph_gen.cc:53][LoadBieModel] Loading bie model. [piano][info][graph_gen.cc:58][LoadBieModel] Creating graph from BIE (version 2.10). [piano][info][graph_gen.cc:145][GraphOptFE] Graph is generated from optimized graph, skip graph optimization [common][info][tgt_graph_gen.cc:31][GraphOptBE] Working on hardware relevant optimizations. [common][info][tgt_graph_gen.cc:43][GraphOptBE] Working on graph post process [common][info][compile.cc:250][CompileImpl] Lowering IR [cmd][info][cmd_node_gen.cc:686][CutAnalysis] Cutting image [fmcut][info][img_cut.cc:65][ImageCut] Start image cut with mode [default] [common][info][compile.cc:253][CompileImpl] Generating weight [common][info][compile.cc:257][CompileImpl] Generating command [cmd][info][cmd_generator.cc:368][GenCmds] Generate commands based on [45] cmd nodes [cmd][info][cmd_generator.cc:1350][RemoveRedundantConfCmd] 949 out of 2108 CONF cmds are optimized out [common][info][compile.cc:276][CompileImpl] input_size [692224], wt_size [9852368], cmd_size [5120], dram_size [1038336], sram_size [524288], fw_code_size [460] info: dram_start: 1610612736 dram_size: 1038336 cmd_start: 0 cmd_size: 5120 input_start: 3145728 input_size: 692224 fw_code_start: 1610612736 fw_code_size: 460 input_num: 0 output_num: 2 output_size: 265200 output_start: 8388608 [common][info][compile.cc:307][CompileImpl] Compilation completed. [tool][info][batch_compile.cc:551][LayoutBins] Re-layout binaries [tool][info][batch_compile.cc:601][LayoutBins] output start: 0x600e9bf0, end: 0x600e9bf0 [tool][info][batch_compile.cc:513][BatchCompile] compiling input.kdp520.scaled.bie [common][info][compile.cc:62][LoadCfg] Loading config. [piano][info][graph_gen.cc:53][LoadBieModel] Loading bie model. [piano][info][graph_gen.cc:58][LoadBieModel] Creating graph from BIE (version 2.10). [piano][info][graph_gen.cc:145][GraphOptFE] Graph is generated from optimized graph, skip graph optimization [common][info][tgt_graph_gen.cc:31][GraphOptBE] Working on hardware relevant optimizations. [common][info][tgt_graph_gen.cc:43][GraphOptBE] Working on graph post process [common][info][compile.cc:250][CompileImpl] Lowering IR [cmd][info][cmd_node_gen.cc:686][CutAnalysis] Cutting image [fmcut][info][img_cut.cc:65][ImageCut] Start image cut with mode [default] [common][info][compile.cc:253][CompileImpl] Generating weight [common][info][compile.cc:257][CompileImpl] Generating command [cmd][info][cmd_generator.cc:368][GenCmds] Generate commands based on [45] cmd nodes [cmd][info][cmd_generator.cc:1350][RemoveRedundantConfCmd] 949 out of 2108 CONF cmds are optimized out [common][info][compile.cc:276][CompileImpl] input_size [692224], wt_size [9852368], cmd_size [5120], dram_size [1038336], sram_size [524288], fw_code_size [460] info: dram_start: 1611570160 dram_size: 1038336 cmd_start: 1612608496 cmd_size: 5120 input_start: 1610612736 input_size: 692224 fw_code_start: 1622465984 fw_code_size: 460 input_num: 0 output_num: 2 output_size: 265200 output_start: 1611304960 [common][info][compile.cc:307][CompileImpl] Compilation completed. [tool][info][batch_compile.cc:711][CombineAllBin] Combine all bin files of all models into all_models.bin [tool][info][batch_compile.cc:787][WriteFwInfo] Generate firmware info to fw_info.txt & fw_info.bin [tool][info][batch_compile.cc:653][VerifyOutput] => 1 models [tool][info][batch_compile.cc:661][VerifyOutput] id: 32769 [tool][info][batch_compile.cc:662][VerifyOutput] version: 0x1 [tool][info][batch_compile.cc:667][VerifyOutput] addr: 0x60000000, size: 0xa9000 [tool][info][batch_compile.cc:667][VerifyOutput] addr: 0x600a9000, size: 0x40bf0 [tool][info][batch_compile.cc:667][VerifyOutput] addr: 0x600e9bf0, size: 0xfd800 [tool][info][batch_compile.cc:667][VerifyOutput] addr: 0x601e73f0, size: 0x1400 [tool][info][batch_compile.cc:667][VerifyOutput] addr: 0x601e87f0, size: 0x9655d0 [tool][info][batch_compile.cc:667][VerifyOutput] addr: 0x60b4ddc0, size: 0x1cc [tool][info][batch_compile.cc:670][VerifyOutput] [tool][info][batch_compile.cc:674][VerifyOutput] end addr 0x60b4df8c, [tool][info][batch_compile.cc:676][VerifyOutput] total bin size 0x966b9c [tool][info][batch_compile.cc:1233][main] batch_compile complete[0] Compile done. Save Nef file to '/data1/kneron_flow/models_520.nef' current node is an NPU INPUT NODE current node is a CPU NODE current node is an NPU INPUT NODE current node is a output NODE current node is a output NODE Info: set output buffer [600a9000, 600b5f30). Info: set output buffer [600b5f30, 600e9bf0). CSIM Version: f23ebbf ---------- start npu ---------- ---------- start cpu ---------- ---- cpu node: cpu_op_type = Upsample ---------- resume npu ---------- ---------- dump output node ---------- ---------- dump output node ---------- done (array([[259.62997, 472.13394, 294.2162 , 523.1737 ], [234.3568 , 225.17163, 307.17825, 374.8361 ]], dtype=float32), array([0.8921604 , 0.67475265], dtype=float32), array([2, 7], dtype=int32))