Can't run pretrained model on Windows

[lamhoangtung]

Hi Siraj, i'm trying to run the pretrained model on my PC. I started up the Udacity self-driving simulator, choose a scene and press the Autonomous Mode button. Then, run the model as python drive.py model.h5. But Python crashed and i got this error

Here is the log: C:\Users\Admin\Downloads\How_to_simulate_a_self_driving_car-master\How_to_simulate_a_self_driving_car-master>python drive.py model.h5 Using TensorFlow backend. 2017-06-08 16:13:51.588745: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE instructions, but these are available on your machine and could speed up CPU computations. 2017-06-08 16:13:51.588821: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE2 instructions, but these are available on your machine and could speed up CPU computations. 2017-06-08 16:13:51.589144: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations. 2017-06-08 16:13:51.589173: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. 2017-06-08 16:13:51.589227: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. 2017-06-08 16:13:52.107390: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:887] Found device 0 with properties: name: GeForce GTX 750 Ti major: 5 minor: 0 memoryClockRate (GHz) 1.2805 pciBusID 0000:01:00.0 Total memory: 2.00GiB Free memory: 1.65GiB 2017-06-08 16:13:52.107474: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:908] DMA: 0 2017-06-08 16:13:52.112770: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:918] 0: Y 2017-06-08 16:13:52.113692: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 750 Ti, pci bus id: 0000:01:00.0) NOT RECORDING THIS RUN ... (8624) wsgi starting up on http://0.0.0.0:4567 (8624) accepted ('127.0.0.1', 51496) connect c98ff781994844a6aa545a78314a4374 2017-06-08 16:14:01.034618: E c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\stream_executor\cuda\cuda_dnn.cc:359] could not create cudnn handle: CUDNN_STATUS_NOT_INITIALIZED 2017-06-08 16:14:01.035909: E c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\stream_executor\cuda\cuda_dnn.cc:366] error retrieving driver version: Unimplemented: kernel reported driver version not implemented on Windows 2017-06-08 16:14:01.036502: E c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\stream_executor\cuda\cuda_dnn.cc:326] could not destroy cudnn handle: CUDNN_STATUS_BAD_PARAM 2017-06-08 16:14:01.037345: F c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\kernels\conv_ops.cc:659] Check failed: stream->parent()->GetConvolveAlgorithms(&algorithms)

How can i fix this problem, i installed all dependencies by manually using pip, BTW, i'm using GPU version of TensorFlow and my GPU is GTX 750Ti. Thanks you <3

[Ilovescienceandpython]

you have a problem with your cuda driver try to run it on the cpu

[lamhoangtung]

Thank @Ilovescienceandpython <3. I will give it a try