NJU-Jet / SR_Mobile_Quantization

Winner solution of mobile AI (CVPRW 2021).
148 stars 41 forks source link

generate_tflite failed #6

Closed Lvhhhh closed 3 years ago

Lvhhhh commented 3 years ago

when run generate_tfilte . it comes error: Connected to pydev debugger (build 202.6948.78) 2021-06-03 06:13:39.240280: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2021-06-03 06:13:39.240442: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. 2021-06-03 06:13:56.370643: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcuda.so.1 2021-06-03 06:13:58.464006: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: pciBusID: 0000:84:00.0 name: TITAN Xp computeCapability: 6.1 coreClock: 1.582GHz coreCount: 30 deviceMemorySize: 11.91GiB deviceMemoryBandwidth: 510.07GiB/s 2021-06-03 06:13:58.464464: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2021-06-03 06:13:58.464742: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublas.so.11'; dlerror: libcublas.so.11: cannot open shared object file: No such file or directory 2021-06-03 06:13:58.464960: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublasLt.so.11'; dlerror: libcublasLt.so.11: cannot open shared object file: No such file or directory 2021-06-03 06:13:58.476443: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcufft.so.10 2021-06-03 06:13:58.477513: I tensorflow/stream_executor/platform/default/dso_loader.cc:53] Successfully opened dynamic library libcurand.so.10 2021-06-03 06:13:58.477765: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusolver.so.11'; dlerror: libcusolver.so.11: cannot open shared object file: No such file or directory 2021-06-03 06:13:58.481692: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusparse.so.11'; dlerror: libcusparse.so.11: cannot open shared object file: No such file or directory 2021-06-03 06:13:58.481940: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory 2021-06-03 06:13:58.481986: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1766] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2021-06-03 06:13:58.507288: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2021-06-03 06:13:58.707850: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-06-03 06:13:58.713893: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264]
2021-06-03 06:14:12.144968: I tensorflow/core/grappler/devices.cc:69] Number of eligible GPUs (core count >= 8, compute capability >= 0.0): 1 2021-06-03 06:14:12.146383: I tensorflow/core/grappler/clusters/single_machine.cc:357] Starting new session 2021-06-03 06:14:12.323394: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: pciBusID: 0000:84:00.0 name: TITAN Xp computeCapability: 6.1 coreClock: 1.582GHz coreCount: 30 deviceMemorySize: 11.91GiB deviceMemoryBandwidth: 510.07GiB/s 2021-06-03 06:14:12.323562: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1766] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2021-06-03 06:14:16.570160: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-06-03 06:14:16.570507: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264] 0 2021-06-03 06:14:16.570664: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0: N 2021-06-03 06:14:16.694057: I tensorflow/core/platform/profile_utils/cpu_utils.cc:114] CPU Frequency: 2100005000 Hz 2021-06-03 06:14:16.766796: I tensorflow/core/grappler/optimizers/meta_optimizer.cc:1144] Optimization results for grappler item: graph_to_optimize function_optimizer: Graph size after: 188 nodes (139), 288 edges (239), time = 46.723ms. function_optimizer: function_optimizer did nothing. time = 0.165ms.

2021-06-03 06:14:19.303393: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:345] Ignored output_format. 2021-06-03 06:14:19.303491: W tensorflow/compiler/mlir/lite/python/tf_tfl_flatbuffer_helpers.cc:348] Ignored drop_control_dependency. 2021-06-03 06:14:19.410415: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:210] disabling MLIR crash reproducer, set env var MLIR_CRASH_REPRODUCER_DIRECTORY to enable. 2021-06-03 06:14:19.670119: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: pciBusID: 0000:84:00.0 name: TITAN Xp computeCapability: 6.1 coreClock: 1.582GHz coreCount: 30 deviceMemorySize: 11.91GiB deviceMemoryBandwidth: 510.07GiB/s 2021-06-03 06:14:19.670482: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1766] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2021-06-03 06:14:19.670555: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix: 2021-06-03 06:14:19.670631: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264] 0 2021-06-03 06:14:19.670664: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0: N representative data: [0]/[5] external/ruy/ruy/apply_multiplier.cc:52: RUY_CHECK_LE condition not satisfied: [ shift <= 7 ] with values [ 16 <= 7 ].

Process finished with exit code 134

what is the possible reason? thank you !

NJU-Jet commented 3 years ago

It seems your cuda version is not compatible with cudnn version. My cuda version is 10.0.130 and cudnn version is 7.6.5