提交 efb2f2ba 编写于 作者: M minqiyang

Fix bugs

test=develop
上级 b420ec3a
develop 2.0.1-rocm-post Ligoml-patch-1 OliverLPH-patch-1 OliverLPH-patch-2 PaddlePM-patch-1 PaddlePM-patch-2 ZHUI-patch-1 add_default_att add_model_benchmark_ci add_some_yaml_config addfile all_new_design_exec ascendrc ascendrelease cherry_undefined_var compile_windows delete_2.0.1-rocm-post delete_add_default_att delete_all_new_design_exec delete_ascendrc delete_compile_windows delete_delete_addfile delete_disable_iterable_dataset_unittest delete_fix_dataloader_memory_leak delete_fix_imperative_dygraph_error delete_fix_retry_ci delete_fix_undefined_var delete_improve_sccache delete_incubate/lite delete_paddle_tiny_install delete_paralleltest delete_prv-disable-more-cache delete_revert-31068-fix_conv3d_windows delete_revert-31562-mean delete_revert-33630-bug-fix delete_revert-34159-add_npu_bce_logical_dev delete_revert-34910-spinlocks_for_allocator delete_revert-35069-revert-34910-spinlocks_for_allocator delete_revert-36057-dev/read_flags_in_ut dingjiaweiww-patch-1 disable_iterable_dataset_unittest dy2static enable_eager_model_test final_state_gen_python_c final_state_intermediate fix-numpy-issue fix_concat_slice fix_dataloader_memory_leak fix_imperative_dygraph_error fix_npu_ci fix_op_flops fix_retry_ci fix_rnn_docs fix_tensor_type fix_undefined_var fixiscan fixiscan1 fixiscan2 fixiscan3 github/fork/123malin/netifaces github/fork/123malin/tdm_abacus github/fork/AshburnLee/dev_unique github/fork/ForFishes/fix_memory_matmul github/fork/ForFishes/rm_fluid github/fork/LielinJiang/move-2.0-api github/fork/LielinJiang/visual-dl-cb github/fork/LiuChiachi/add-transformer-generate-square-subsequent-mask-api github/fork/LiuChiachi/fix-example-code-for-hapi-Model github/fork/LiuChiachi/remove-input-requirment-in-dygraph-Model github/fork/MrChengmo/fix_ps_profiler github/fork/MrChengmo/update_ps_heter github/fork/PWhiddy/patch-1 github/fork/Shixiaowei02/dev/save_load_upgrade github/fork/TCChenlong/fix_hapi github/fork/TCChenlong/fix_inden github/fork/Thunderbrook/xpu_slice github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_2 github/fork/XieYunshen/disable_ut_test_parallel_executor_fetch_isolated_var_3 github/fork/XieYunshen/timeout_20S_ut github/fork/ZeyuChen/remove-nltk github/fork/arlesniak/arlesniak/selective__mkldnn_flags github/fork/baiyfbupt/code_doc_mig github/fork/chalsliu/set_timeout github/fork/chen-zhiyu/develop github/fork/chenwhql/ci/try_to_find_test_buffer_shared_memory_reuse_pass_error github/fork/chenwhql/dygraph/remove_scale_loss_and_apply_collective_grads github/fork/chenwhql/saveload/add_get_inference_program github/fork/chenwhql/saveload/remove_save_load_config github/fork/cryoco/pass-compatibility-trt github/fork/danleifeng/isempty_api2.0 github/fork/frankwhzhang/api_transfer github/fork/hbwx24/error_msg/cuda_kernel_error_msg github/fork/heavengate/cherry_yolo_box github/fork/heavengate/update_yolo_box github/fork/iclementine/rnn_fix github/fork/iducn/testestse github/fork/jczaja/prv-25537-fix github/fork/jeff41404/release/1.8 github/fork/jiweibo/api_2.0 github/fork/jiweibo/fix_lite_resnet50_test github/fork/juncaipeng/fix_doc_1 github/fork/lfchener/sample_code github/fork/littletomatodonkey/fix_reg_doc github/fork/liym27/dy2stat_update_assign_to_rc20 github/fork/luotao1/profiler_ut github/fork/mapingshuo/add_wait github/fork/mapingshuo/doc_2.0 github/fork/mapingshuo/zero-0.5 github/fork/miraiwk/dev github/fork/pangyoki/add-Categorical-class-branch github/fork/pangyoki/add-multinomial-op-branch github/fork/pangyoki/fix-test_distritbution-CI github/fork/qjing666/doublegrad github/fork/qjing666/fix_hdfs_download github/fork/sandyhouse/add_gather_etc github/fork/sandyhouse/add_send_recv_alltoall_etc github/fork/sandyhouse/pipeline_exe_run github/fork/seiriosPlus/feature/large_scale_kv_save_delta github/fork/seiriosPlus/fix/paddle_errors_fix github/fork/seiriosPlus/fix/paddle_op_errors github/fork/shangzhizhou/fix_test_activation_op_random_bug github/fork/smallv0221/yxp0924 github/fork/smallv0221/yxp0925 github/fork/swtkiwi/del-matplotlib github/fork/tianshuo78520a/kunlun_test github/fork/tianshuo78520a/update_dockerfile github/fork/wanghaoshuang/bert_fuse github/fork/wanghaoshuang/label_smooth github/fork/wanghuancoder/develop_CUDASynchronize github/fork/wanghuancoder/develop_Layer_doc github/fork/wanghuancoder/develop_ParameterList_doc github/fork/wanghuancoder/develop_Sequential_doc github/fork/wanghuancoder/develop_bilinear_tensor_product github/fork/wanghuancoder/develop_coverage_build_sh github/fork/wanghuancoder/develop_in_dynamic_mode_doc github/fork/wanghuancoder/develop_unique_name_doc github/fork/wangxicoding/fleet_meta_combine github/fork/wawltor/error_message_fix_5 github/fork/willthefrog/remove_l2_norm github/fork/windstamp/momentum_op github/fork/windstamp/mv_op_5 github/fork/windstamp/normal_api github/fork/wojtuss/wojtuss/fusion_gru_quantization github/fork/wojtuss/wojtuss/quantization-with-shift github/fork/wzzju/fix_err_info github/fork/wzzju/pure_fp16 github/fork/xiemoyuan/op_error_message github/fork/xiemoyuan/optimize_error_message github/fork/yaoxuefeng6/fix_doc github/fork/yaoxuefeng6/mod_dataset_v2 github/fork/yongqiangma/lod github/fork/ysh329/fix-clip-by-norm-error github/fork/ysh329/fix-error-clip-by-value github/fork/yukavio/error_info github/fork/zhangting2020/conv_filter_grad github/fork/zhangting2020/is_compile_with_cuda github/fork/zhangting2020/place_doc github/fork/zhangting2020/program github/fork/zhhsplendid/fix_any github/fork/zhhsplendid/refine_api2 github/fork/zhhsplendid/refine_api2_test github/fork/zhhsplendid/refine_api_test_ptb_lm github/fork/zhhsplendid/refine_api_test_resnet github/fork/zhhsplendid/refine_api_test_simnet github/fork/zhiqiu/dev/refine_initializer github/fork/zhiqiu/dev/remove_inplace_argument github/fork/zlsh80826/nvinfer_plugin_var_len_cuda11 improve_sccache incubate/infrt incubate/lite inplace_addto make_flag_adding_easier move_embedding_to_phi move_histogram_to_pten move_sgd_to_phi move_slice_to_pten move_temporal_shift_to_phi move_yolo_box_to_phi npu_fix_alloc numel paddle_tiny_install paralleltest preln_ernie prv-disable-more-cache prv-md-even-more prv-onednn-2.5 pten_tensor_refactor release/1.4 release/1.5 release/1.6 release/1.7 release/1.8 release/2.0 release/2.0-alpha release/2.0-beta release/2.0-rc release/2.0-rc1 release/2.1 release/2.2 release/2.3 release/2.3-fc-ernie-fix release/2.4 release/lite-0.1 revert-24981-add_device_attr_for_regulization revert-26856-strategy_example2 revert-27520-disable_pr revert-31068-fix_conv3d_windows revert-31562-mean revert-32290-develop-hardlabel revert-33037-forci revert-33475-fix_cifar_label_dimension revert-33630-bug-fix revert-34159-add_npu_bce_logical_dev revert-34406-add_copy_from_tensor revert-34910-spinlocks_for_allocator revert-35069-revert-34910-spinlocks_for_allocator revert-36057-dev/read_flags_in_ut revert-36201-refine_fast_threaded_ssa_graph_executor revert-36985-add_license revert-37318-refactor_dygraph_to_eager revert-37926-eager_coreops_500 revert-37956-revert-37727-pylayer_support_tuple revert-38100-mingdong revert-38301-allocation_rearrange_pr revert-38703-numpy_bf16_package_reupload revert-38732-remove_useless_header_in_elementwise_mul_grad revert-38959-Reduce_Grad revert-39143-adjust_empty revert-39227-move_trace_op_to_pten revert-39268-dev/remove_concat_fluid_kernel revert-40170-support_partial_grad revert-41056-revert-40727-move_some_activaion_to_phi revert-41065-revert-40993-mv_ele_floordiv_pow revert-41068-revert-40790-phi_new revert-41944-smaller_inference_api_test revert-42149-do-not-reset-default-stream-for-stream-safe-cuda-allocator revert-43155-fix_ut_tempfile revert-43882-revert-41944-smaller_inference_api_test revert-45808-phi/simplify_size_op revert-46827-deform_comment rocm_dev_0217 support_weight_transpose test_benchmark_ci test_feature_precision_test_c test_model_benchmark test_model_benchmark_ci zhiqiu-patch-1 v2.4.0-rc0 v2.3.2 v2.3.1 v2.3.0 v2.3.0-rc0 v2.2.2 v2.2.1 v2.2.0 v2.2.0-rc0 v2.2.0-bak0 v2.1.3 v2.1.2 v2.1.1 v2.1.0 v2.1.0-rc0 v2.0.2 v2.0.1 v2.0.0 v2.0.0-rc1 v2.0.0-rc0 v2.0.0-beta0 v2.0.0-alpha0 v1.8.5 v1.8.4 v1.8.3 v1.8.2 v1.8.1 v1.8.0 v1.7.2 v1.7.1 v1.7.0 v1.6.3 v1.6.2 v1.6.1 v1.6.0 v1.6.0-rc0 v1.5.2 v1.5.1 v1.5.0 v1.4.1 v1.4.0 lite-v0.1
无相关合并请求
......@@ -118,19 +118,16 @@ class Autograd {
while (!ready.empty()) {
OpBase* ready_op = ready.front();
ready.pop_front();
LOG(ERROR) << "ApplyGrad Start";
std::map<std::string, std::vector<VarBase*>> input_grads =
ready_op->ApplyGrad();
for (auto it : input_grads) {
const std::vector<VarBase*>& ingrads = it.second;
LOG(ERROR) << "XX";
for (size_t i = 0; i < ingrads.size(); ++i) {
if (!ingrads[i]) continue;
if (ready_op->input_vars_[it.first][i]->IsStopGradient()) {
continue;
}
LOG(ERROR) << "XX";
OpBase* pre_op = ready_op->pre_ops_[it.first][i];
if (!pre_op) continue;
......@@ -140,13 +137,10 @@ class Autograd {
if (pre_op_ready) {
ready.push_back(pre_op);
}
LOG(ERROR) << "XX";
}
}
ready_op->InvokeBackwardHooks();
LOG(ERROR) << "ApplyGrad End";
}
}
......@@ -219,6 +213,7 @@ std::map<std::string, std::vector<VarBase*>> OpBase::ApplyGrad() {
return {};
}
VLOG(3) << "apply op grad: " << op_desc_->Type();
std::vector<framework::VariableValueMap> grad_outputs;
if (backward_id_ > 0) {
VLOG(3) << "py_layer_grad";
......@@ -229,10 +224,8 @@ std::map<std::string, std::vector<VarBase*>> OpBase::ApplyGrad() {
grad_input_vars_[0][framework::GradVarName(PyLayer::kFwdInp)]);
} else {
grad_outputs.resize(grad_op_descs_.size());
LOG(ERROR) << "ApplyGrad " << grad_op_descs_.size();
for (size_t k = 0; k < grad_op_descs_.size(); ++k) {
framework::OpDesc* grad_op_desc = grad_op_descs_[k];
LOG(ERROR) << "op grad " << grad_op_desc->Type();
VLOG(3) << "op grad " << grad_op_desc->Type();
for (auto it : grad_output_vars_[k]) {
auto& outputs = grad_outputs[k][it.first];
......@@ -244,16 +237,12 @@ std::map<std::string, std::vector<VarBase*>> OpBase::ApplyGrad() {
}
}
LOG(ERROR) << "op grad " << grad_op_desc->Type();
framework::RuntimeContext ctx(grad_input_vars_[k], grad_outputs[k]);
// No need to do compile time infer shape here.
// grad_op_desc_->InferShape(*block_);
grad_op_desc->InferVarType(block_);
LOG(ERROR) << "op grad " << grad_op_desc->Type();
std::unique_ptr<framework::OperatorBase> opbase =
framework::OpRegistry::CreateOp(*grad_op_desc);
framework::OperatorWithKernel* op_kernel =
......@@ -267,8 +256,6 @@ std::map<std::string, std::vector<VarBase*>> OpBase::ApplyGrad() {
}
}
LOG(ERROR) << "delete grad start ";
for (size_t k = 0; k < grad_output_vars_.size(); ++k) {
for (auto it : grad_output_vars_[k]) {
auto& outputs = grad_outputs[k][it.first];
......@@ -288,18 +275,16 @@ std::map<std::string, std::vector<VarBase*>> OpBase::ApplyGrad() {
}
void OpBase::InvokeBackwardHooks() {
LOG(ERROR) << "call backward start ";
VLOG(3) << "call backward hooks, hooks num: " << backward_hooks_.size();
// call backward hooks
for (py::object& callable : backward_hooks_) {
callable(this);
}
LOG(ERROR) << "call backward end ";
}
void OpBase::RegisterBackwardHooks(const py::object& callable) {
LOG(ERROR) << "Register backward hooks " << trace_id_;
VLOG(3) << "Register backward hooks " << trace_id_;
// TODO(minqiyang): check the callable format
backward_hooks_.push_back(callable);
......
......@@ -125,8 +125,6 @@ class VarBase {
public:
virtual ~VarBase() {
LOG(ERROR) << "remove var " << name_.c_str();
if (block_) {
block_->RemoveVar(name_);
}
......@@ -216,13 +214,9 @@ class PYBIND11_HIDDEN OpBase {
delete desc;
}
LOG(ERROR) << "remove op " << op_desc_->Type() << " id " << trace_id_;
if (block_) {
block_->RemoveOpInternal(op_desc_);
}
LOG(ERROR) << "remove op end " << trace_id_;
}
std::map<std::string, std::vector<VarBase*>> ApplyGrad();
......
......@@ -154,6 +154,7 @@ std::set<std::string> Tracer::Trace(OpBase* op, const VarBasePtrMap& inputs,
op->grad_input_vars_.resize(op->grad_op_descs_.size());
op->grad_output_vars_.resize(op->grad_op_descs_.size());
for (size_t i = 0; i < op->grad_op_descs_.size(); ++i) {
framework::OpDesc* grad_op_desc = op->grad_op_descs_[i];
for (auto it : grad_op_desc->Inputs()) {
......@@ -166,7 +167,6 @@ std::set<std::string> Tracer::Trace(OpBase* op, const VarBasePtrMap& inputs,
PADDLE_ENFORCE(fwd_var_it != vars.end());
// Forward inputs or outputs.
grad_in_vars.push_back(fwd_var_it->second->var_);
vars_saved_for_backward.insert(it.first);
} else {
VarBase* var = vars[var_it->second];
if (!var->grads_->var_->IsInitialized()) {
......@@ -176,6 +176,8 @@ std::set<std::string> Tracer::Trace(OpBase* op, const VarBasePtrMap& inputs,
// Douts.
grad_in_vars.push_back(var->grads_->var_);
}
vars_saved_for_backward.insert(it.first);
}
}
......
......@@ -173,7 +173,6 @@ PYBIND11_MODULE(core, m) {
[](const imperative::VarBase &self) { return self.name_; },
[](imperative::VarBase &self, const std::string &name) {
self.name_ = name;
LOG(ERROR) << "create ivar name " << self.name_;
})
.def_property("block",
[](const imperative::VarBase &self) { return self.block_; },
......
......@@ -12,6 +12,8 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from __future__ import print_function
import contextlib
import unittest
import numpy as np
......@@ -146,69 +148,69 @@ class TestImperativeMnist(unittest.TestCase):
for param in mnist.parameters():
dy_param_value[param.name] = param._numpy()
# with new_program_scope():
# fluid.default_startup_program().random_seed = seed
# fluid.default_main_program().random_seed = seed
# exe = fluid.Executor(fluid.CPUPlace(
# ) if not core.is_compiled_with_cuda() else fluid.CUDAPlace(0))
# mnist = MNIST("mnist")
# sgd = SGDOptimizer(learning_rate=1e-3)
# train_reader = paddle.batch(
# paddle.dataset.mnist.train(), batch_size=128, drop_last=True)
# img = fluid.layers.data(
# name='pixel', shape=[1, 28, 28], dtype='float32')
# label = fluid.layers.data(name='label', shape=[1], dtype='int64')
# cost = mnist(img)
# loss = fluid.layers.cross_entropy(cost, label)
# avg_loss = fluid.layers.mean(loss)
# sgd.minimize(avg_loss)
# # initialize params and fetch them
# static_param_init_value = {}
# static_param_name_list = []
# for param in mnist.parameters():
# static_param_name_list.append(param.name)
# out = exe.run(fluid.default_startup_program(),
# fetch_list=static_param_name_list)
# for i in range(len(static_param_name_list)):
# static_param_init_value[static_param_name_list[i]] = out[i]
# for epoch in range(epoch_num):
# for batch_id, data in enumerate(train_reader()):
# static_x_data = np.array(
# [x[0].reshape(1, 28, 28)
# for x in data]).astype('float32')
# y_data = np.array(
# [x[1] for x in data]).astype('int64').reshape([128, 1])
# fetch_list = [avg_loss.name]
# fetch_list.extend(static_param_name_list)
# out = exe.run(
# fluid.default_main_program(),
# feed={"pixel": static_x_data,
# "label": y_data},
# fetch_list=fetch_list)
# static_param_value = {}
# static_out = out[0]
# for i in range(1, len(out)):
# static_param_value[static_param_name_list[i - 1]] = out[
# i]
# self.assertTrue(np.allclose(dy_x_data.all(), static_x_data.all()))
# for key, value in six.iteritems(static_param_init_value):
# self.assertTrue(np.allclose(value, dy_param_init_value[key]))
# self.assertTrue(np.allclose(static_out, dy_out))
# for key, value in six.iteritems(static_param_value):
# self.assertTrue(np.allclose(value, dy_param_value[key], atol=1e-5))
with new_program_scope():
fluid.default_startup_program().random_seed = seed
fluid.default_main_program().random_seed = seed
exe = fluid.Executor(fluid.CPUPlace(
) if not core.is_compiled_with_cuda() else fluid.CUDAPlace(0))
mnist = MNIST("mnist")
sgd = SGDOptimizer(learning_rate=1e-3)
train_reader = paddle.batch(
paddle.dataset.mnist.train(), batch_size=128, drop_last=True)
img = fluid.layers.data(
name='pixel', shape=[1, 28, 28], dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')
cost = mnist(img)
loss = fluid.layers.cross_entropy(cost, label)
avg_loss = fluid.layers.mean(loss)
sgd.minimize(avg_loss)
# initialize params and fetch them
static_param_init_value = {}
static_param_name_list = []
for param in mnist.parameters():
static_param_name_list.append(param.name)
out = exe.run(fluid.default_startup_program(),
fetch_list=static_param_name_list)
for i in range(len(static_param_name_list)):
static_param_init_value[static_param_name_list[i]] = out[i]
for epoch in range(epoch_num):
for batch_id, data in enumerate(train_reader()):
static_x_data = np.array(
[x[0].reshape(1, 28, 28)
for x in data]).astype('float32')
y_data = np.array(
[x[1] for x in data]).astype('int64').reshape([128, 1])
fetch_list = [avg_loss.name]
fetch_list.extend(static_param_name_list)
out = exe.run(
fluid.default_main_program(),
feed={"pixel": static_x_data,
"label": y_data},
fetch_list=fetch_list)
static_param_value = {}
static_out = out[0]
for i in range(1, len(out)):
static_param_value[static_param_name_list[i - 1]] = out[
i]
self.assertTrue(np.allclose(dy_x_data.all(), static_x_data.all()))
for key, value in six.iteritems(static_param_init_value):
self.assertTrue(np.allclose(value, dy_param_init_value[key]))
self.assertTrue(np.allclose(static_out, dy_out))
for key, value in six.iteritems(static_param_value):
self.assertTrue(np.allclose(value, dy_param_value[key], atol=1e-5))
if __name__ == '__main__':
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册
反馈
建议
客服 返回
顶部