UI web about GPU

[diaodeyi]

2021-02-22 17:07:53.619219: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED 2021-02-22 17:07:53.620372: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED 2021-02-22 17:07:53.628342: E tensorflow/stream_executor/cuda/cuda_blas.cc:238] failed to create cublas handle: CUBLAS_STATUS_ALLOC_FAILED 2021-02-22 17:07:53.628367: W tensorflow/stream_executor/stream.cc:2041] attempting to perform BLAS operation using StreamExecutor without BLAS support 2021-02-22 17:08:00.180799: I tensorflow/stream_executor/stream.cc:1990] [stream=0x7f8122a33dc0,impl=0x7f8122a33440] did not wait for [stream=0x7f8122a33b40,impl=0x7f8122a32790] 2021-02-22 17:08:00.180867: I tensorflow/stream_executor/stream.cc:4938] [stream=0x7f8122a33dc0,impl=0x7f8122a33440] did not memcpy host-to-device; source: 0x7f7bfea34d80 2021-02-22 17:08:00.180986: F tensorflow/core/common_runtime/gpu/gpu_util.cc:342] CPU->GPU Memcpy failed [1] 26566 abort (core dumped) streamlit run app.py

it seems the 6Gx2 TITAN XP are not enough for the web UI?

[diaodeyi]

Is there anyone can run the web UI successfully？ we can have some communication

[diaodeyi]

2 root error(s) found. (0) Internal: Blas GEMM launch failed : a.shape=(1, 512), b.shape=(512, 32), m=1, n=32, k=512 [[node G_synthesis_1/_Run/G_synthesis/1024x1024/Conv1/MatMul (defined at /home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]] [[G_synthesis_1/_Run/saturate_cast/_1521]] (1) Internal: Blas GEMM launch failed : a.shape=(1, 512), b.shape=(512, 32), m=1, n=32, k=512 [[node G_synthesis_1/_Run/G_synthesis/1024x1024/Conv1/MatMul (defined at /home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:1748) ]] 0 successful operations. 0 derived errors ignored. Original stack trace for 'G_synthesis_1/_Run/G_synthesis/1024x1024/Conv1/MatMul': File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/threading.py", line 885, in _bootstrap self._bootstrap_inner() File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/threading.py", line 917, in _bootstrap_inner self.run() File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/threading.py", line 865, in run self._target(*self._args, self._kwargs) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/script_runner.py", line 162, in _process_request_queue self._run_script(data) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/script_runner.py", line 332, in _run_script exec(code, module.dict) File "/data1/code2/StyleFlow/webui/app.py", line 312, in main() File "/data1/code2/StyleFlow/webui/app.py", line 254, in main img_source = generate_image(session, model, w_selected) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/caching.py", line 606, in wrapped_func return get_or_create_cached_value() File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/caching.py", line 588, in get_or_create_cached_value return_value = func(*args, *kwargs) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 43, in decorate_no_grad return func(args, kwargs) File "/data1/code2/StyleFlow/webui/app.py", line 139, in generate_image img = model.generate_im_from_w_space(w)[0].copy() File "../utils.py", line 250, in generate_im_from_w_space images = self.Gs.components.synthesis.run(w, self.Gs_syn_kwargs) File "../dnnlib/tflib/network.py", line 417, in run out_gpu = net_gpu.get_output_for(*in_gpu, return_as_list=True, *dynamic_kwargs) File "../dnnlib/tflib/network.py", line 221, in get_output_for out_expr = self._build_func(final_inputs, build_kwargs) File "", line 498, in G_synthesis_stylegan2 File "", line 470, in block File "", line 455, in layer File "", line 98, in modulated_conv2d_layer File "", line 46, in dense_layer File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/util/dispatch.py", line 180, in wrapper return target(*args, kwargs) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/ops/math_ops.py", line 2754, in matmul a, b, transpose_a=transpose_a, transpose_b=transpose_b, name=name) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/ops/gen_math_ops.py", line 6136, in mat_mul name=name) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper op_def=op_def) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func return func(*args, *kwargs) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op attrs, op_def, compute_device) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal op_def=op_def) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line 1748, in init self._traceback = tf_stack.extract_stack() Traceback: File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/script_runner.py", line 332, in _run_script exec(code, module.dict) File "/data1/code2/StyleFlow/webui/app.py", line 312, in main() File "/data1/code2/StyleFlow/webui/app.py", line 254, in main img_source = generate_image(session, model, w_selected) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/caching.py", line 606, in wrapped_func return get_or_create_cached_value() File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/streamlit/caching.py", line 588, in get_or_create_cached_value return_value = func(args, kwargs) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/torch/autograd/grad_mode.py", line 43, in decorate_no_grad return func(*args, kwargs) File "/data1/code2/StyleFlow/webui/app.py", line 139, in generate_image img = model.generate_im_from_w_space(w)[0].copy() File "../utils.py", line 250, in generate_im_from_w_space images = self.Gs.components.synthesis.run(w, self.Gs_syn_kwargs) File "../dnnlib/tflib/network.py", line 442, in run mb_out = tf.get_default_session().run(out_expr, dict(zip(in_expr, mb_in))) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 956, in run run_metadata_ptr) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run feed_dict_tensor, options, run_metadata) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run run_metadata) File "/home/rjs/.conda/envs/StyleFlow/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call raise type(e)(node_def, op, message)

this is the detail about the issure in the web

[diaodeyi]

My GPU is 6GB TiTAN（i have two，but it seems do not support muti-GPU）， I want to if it's enough for web gui？

[zhywanna]

Same. Did you solve this problem?