clean cmake building errors

mindspore/lite/src/ops/addn.cc

@@ -48,7 +48,7 @@ int AddN::InferShape(std::vector<tensor::Tensor *> inputs, std::vector<tensor::T
   if (!GetInferFlag()) {
     return RET_OK;
   }
-  for (int i = 1; i < inputs.size(); ++i) {
+  for (size_t i = 1; i < inputs.size(); ++i) {
     if (inputs.at(i)->shape() != inputs.at(0)->shape()) {
       MS_LOG(ERROR) << "AddN inputs shape is not equal!";
       return RET_INPUT_TENSOR_ERROR;

mindspore/lite/src/ops/argmax.cc

@@ -63,7 +63,7 @@ int ArgMax::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor
   }
   std::vector<int> output_shape(input->shape());
   auto input_shape_size = input->shape().size();
-  int axis = GetAxis() < 0 ? GetAxis() + input_shape_size : GetAxis();
+  auto axis = GetAxis() < 0 ? GetAxis() + input_shape_size : GetAxis();
   if (axis >= input_shape_size || axis < 0) {
     MS_LOG(ERROR) << "Invalid axis " << GetAxis() << ", input shape size: " << input_shape_size;
     return RET_PARAM_INVALID;

mindspore/lite/src/ops/argmin.cc

@@ -61,7 +61,7 @@ int ArgMin::InferShape(std::vector<lite::tensor::Tensor *> inputs_, std::vector<
     return RET_OK;
   }
   auto input_shape_size = input->shape().size();
-  int axis = GetAxis() < 0 ? GetAxis() + input_shape_size : GetAxis();
+  auto axis = GetAxis() < 0 ? GetAxis() + input_shape_size : GetAxis();
   if (axis >= input_shape_size || axis < 0) {
     MS_LOG(ERROR) << "Invalid axis " << GetAxis() << ", input shape size: " << input_shape_size;
     return RET_PARAM_INVALID;

mindspore/lite/src/ops/arithmetic.cc

@@ -55,7 +55,7 @@ int Arithmetic::InferShape(std::vector<lite::tensor::Tensor *> inputs_, std::vec
     ndim_ = input_shape1.size();
     auto fill_dim_num = input_shape1.size() - input_shape0.size();
     int j = 0;
-    for (int i = 0; i < input_shape1.size(); i++) {
+    for (size_t i = 0; i < input_shape1.size(); i++) {
       if (i < fill_dim_num) {
         in_shape0_[i] = 1;
       } else {
@@ -68,7 +68,7 @@ int Arithmetic::InferShape(std::vector<lite::tensor::Tensor *> inputs_, std::vec
     ndim_ = input_shape0.size();
     auto fill_dim_num = input_shape0.size() - input_shape1.size();
     int j = 0;
-    for (int i = 0; i < input_shape0.size(); i++) {
+    for (size_t i = 0; i < input_shape0.size(); i++) {
       if (i < fill_dim_num) {
         in_shape1_[i] = 1;
       } else {
@@ -77,14 +77,14 @@ int Arithmetic::InferShape(std::vector<lite::tensor::Tensor *> inputs_, std::vec
       in_shape0_[i] = input_shape0[i];
     }
   } else {
-    for (int i = 0; i < input_shape0.size(); i++) {
+    for (size_t i = 0; i < input_shape0.size(); i++) {
       in_shape1_[i] = input_shape1[i];
       in_shape0_[i] = input_shape0[i];
     }
   }
 
   std::vector<int> output_shape;
-  for (size_t i = 0; i < ndim_; i++) {
+  for (int i = 0; i < ndim_; i++) {
     if (in_shape0_[i] != in_shape1_[i]) {
       if (in_shape0_[i] == 1) {
         out_shape_[i] = in_shape1_[i];

mindspore/lite/src/ops/batch_to_space.cc

@@ -85,7 +85,7 @@ int BatchToSpace::InferShape(std::vector<lite::tensor::Tensor *> inputs, std::ve
     MS_LOG(ERROR) << "Crops size should be " << kCropsSize;
     return RET_PARAM_INVALID;
   }
-  size_t mul_block_shape = 1;
+  int mul_block_shape = 1;
 
   for (size_t i = 0; i < kBlockShapeSize; ++i) {
     if (block_shape[i] <= 0) {

mindspore/lite/src/ops/concat.cc

@@ -58,7 +58,7 @@ int Concat::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor
 
   MS_ASSERT(concat_prim != nullptr);
   auto input0_shape = inputs_.at(0)->shape();
-  int axis = GetAxis() < 0 ? GetAxis() + input0_shape.size() : GetAxis();
+  auto axis = GetAxis() < 0 ? GetAxis() + input0_shape.size() : GetAxis();
   if (axis < 0 || axis >= input0_shape.size()) {
     MS_LOG(ERROR) << "Invalid axis: " << axis;
     return RET_PARAM_INVALID;

mindspore/lite/src/ops/embedding_lookup.cc

@@ -58,7 +58,7 @@ int EmbeddingLookup::InferShape(std::vector<tensor::Tensor *> inputs_, std::vect
   for (size_t i = 0; i < embedding_shape.size(); ++i) {
     output_shape.push_back(embedding_shape.at(i));
   }
-  for (int i = 1; i < inputs_.size() - 1; ++i) {
+  for (size_t i = 1; i < inputs_.size() - 1; ++i) {
     auto embedding_shape_t = inputs_.at(i)->shape();
     embedding_shape_t.erase(embedding_shape_t.begin());
     if (embedding_shape_t != embedding_shape) {

mindspore/lite/src/ops/expand_dims.cc

@@ -51,7 +51,7 @@ int ExpandDims::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<te
   if (dim < 0) {
     dim += input->shape().size() + 1;
   }
-  if (dim > input->shape().size()) {
+  if (dim > static_cast<int>(input->shape().size())) {
     MS_LOG(ERROR) << "attribute dim out of range";
     return RET_INPUT_TENSOR_ERROR;
   }

mindspore/lite/src/ops/flatten.cc

@@ -42,7 +42,7 @@ int Flatten::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tenso
   std::vector<int> output_shape(2);
   output_shape[0] = input_shape[0];
   output_shape[1] = 1;
-  for (int i = 1; i < input_shape.size(); i++) {
+  for (size_t i = 1; i < input_shape.size(); i++) {
     output_shape[1] *= input_shape[i];
   }
   output->set_shape(output_shape);

mindspore/lite/src/ops/full_connection.cc

@@ -60,7 +60,7 @@ int FullConnection::InferShape(std::vector<lite::tensor::Tensor *> inputs_,
     MS_LOG(ERROR) << "Input tensors num error";
     return 1;
   }
-  if (GetAxis() < 1 || GetAxis() > input0->shape().size()) {
+  if (GetAxis() < 1 || GetAxis() > static_cast<int>(input0->shape().size())) {
     MS_LOG(ERROR) << "FullConnection axis invalid";
     return 1;
   }

mindspore/lite/src/ops/gather.cc

@@ -83,7 +83,7 @@ int Gather::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor
   }
   std::vector<int> out_shape{in_shape};
   out_shape.erase(out_shape.begin() + axis);
-  for (size_t i = 0; i < indices_rank; i++) {
+  for (int i = 0; i < indices_rank; i++) {
     out_shape.insert(out_shape.begin() + axis, indices_shape[i]);
   }
   output->set_shape(out_shape);

mindspore/lite/src/ops/matmul.cc

@@ -56,7 +56,7 @@ int MatMul::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor
     MS_LOG(ERROR) << "inputs shape is invalid";
     return RET_INPUT_TENSOR_ERROR;
   }
-  for (int i = 0; i < a_shape.size() - 2; ++i) {
+  for (size_t i = 0; i < a_shape.size() - 2; ++i) {
     if (a_shape[i] != b_shape[i]) {
       MS_LOG(ERROR) << "Op MatMul's dimensions must be equal";
       return RET_INPUT_TENSOR_ERROR;

mindspore/lite/src/ops/mean.cc

@@ -67,7 +67,7 @@ int Mean::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor::
   // reduce on all axes
   if (num_axes == 0) {
     if (keep_dims) {
-      for (auto i = 0; i < in_shape.size(); i++) {
+      for (size_t i = 0; i < in_shape.size(); i++) {
         out_shape.push_back(1);
       }
     }
@@ -78,7 +78,7 @@ int Mean::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor::
   // reduce on selected axes
   for (size_t i = 0; i < in_shape.size(); i++) {
     bool reduce_axis = false;
-    for (int idx = 0; idx < num_axes; ++idx) {
+    for (size_t idx = 0; idx < num_axes; ++idx) {
       if (static_cast<size_t>(axes[idx]) == i) {
         reduce_axis = true;
         break;

mindspore/lite/src/ops/prior_box.cc

@@ -110,7 +110,7 @@ int PriorBox::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tens
   std::vector<float> different_aspect_ratios{1.0f};
   auto aspect_ratios = GetAspectRatios();
   MS_ASSERT(aspect_ratios != nullptr);
-  for (auto i = 0; i < aspect_ratios.size(); i++) {
+  for (size_t i = 0; i < aspect_ratios.size(); i++) {
     float ratio = aspect_ratios[i];
     bool exist = std::any_of(different_aspect_ratios.begin(), different_aspect_ratios.end(),
                              [&](float v) { return abs(ratio - v) < 1e-6; });

mindspore/lite/src/ops/reduce.cc

@@ -71,7 +71,7 @@ int Reduce::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor
   // reduce on all axes
   if (num_axes == 0) {
     if (keep_dims) {
-      for (auto i = 0; i < in_shape.size(); i++) {
+      for (size_t i = 0; i < in_shape.size(); i++) {
         out_shape.push_back(1);
       }
     }
@@ -82,7 +82,7 @@ int Reduce::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor
   // reduce on selected axes
   for (size_t i = 0; i < in_shape.size(); i++) {
     bool reduce_axis = false;
-    for (int idx = 0; idx < num_axes; ++idx) {
+    for (size_t idx = 0; idx < num_axes; ++idx) {
       if (static_cast<size_t>(axes[idx]) == i || static_cast<size_t>(axes[idx] + in_shape.size()) == i) {
         reduce_axis = true;
         break;

mindspore/lite/src/ops/reshape.cc

@@ -80,15 +80,15 @@ void CalShape(const T *data, const std::vector<tensor::Tensor *> &inputs, std::v
   int input_count = inputs[0]->ElementsNum();
   int index = 0;
   int size = 1;
-  for (size_t i = 0; i < shape_size; i++) {
+  for (int i = 0; i < shape_size; i++) {
-    if (data[i] == -1) {
+    if (static_cast<int>(data[i]) == -1) {
       index = i;
     } else {
       size *= data[i];
     }
     out_shape->push_back(data[i]);
   }
-  if (data[index] == -1) {
+  if (static_cast<int>(data[index]) == -1) {
     (*out_shape)[index] = input_count / size;
   }
 }

mindspore/lite/src/ops/slice.cc

@@ -67,7 +67,7 @@ int SliceOp::InferShape(std::vector<lite::tensor::Tensor *> inputs, std::vector<
   std::vector<int32_t> slice_begin(GetBegin().begin(), GetBegin().end());
   std::vector<int32_t> slice_size(GetSize().begin(), GetSize().end());
   std::vector<int32_t> output_shape(input_shape.size());
-  for (int i = 0; i < input_shape.size(); ++i) {
+  for (size_t i = 0; i < input_shape.size(); ++i) {
     if (slice_size[i] < 0 && slice_size[i] != -1) {
       MS_LOG(ERROR) << "Invalid size input!size[" << i << "]=" << slice_size[i];
       return RET_PARAM_INVALID;

mindspore/lite/src/ops/split.cc

@@ -62,7 +62,7 @@ int Split::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor:
     return RET_ERROR;
   }
   int number_split = spilt_prim->numberSplit();
-  if (outputs_.size() != number_split) {
+  if (static_cast<int>(outputs_.size()) != number_split) {
     MS_LOG(ERROR) << "outputs number is not equal to " << number_split;
     return RET_ERROR;
   }

mindspore/lite/src/ops/squeeze.cc

@@ -62,15 +62,15 @@ int Squeeze::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tenso
     axes_.push_back(*iter);
   }
   if (axes_.size() == 0) {
-    for (int i = 0; i < in_shape.size(); i++) {
+    for (size_t i = 0; i < in_shape.size(); i++) {
       if (in_shape[i] != 1) {
         out_shape.push_back(in_shape[i]);
       }
     }
   } else {
-    int axisIdx = 0;
+    size_t axisIdx = 0;
-    for (int i = 0; i < in_shape.size(); i++) {
+    for (size_t i = 0; i < in_shape.size(); i++) {
-      if (axisIdx < axes_.size() && axes_[axisIdx] == i) {
+      if (axisIdx < axes_.size() && axes_[axisIdx] == static_cast<int>(i)) {
         MS_ASSERT(in_shape[i] == 1);
         axisIdx++;
         continue;

mindspore/lite/src/ops/stack.cc

@@ -64,7 +64,7 @@ int Stack::InferShape(std::vector<tensor::Tensor *> inputs, std::vector<tensor::
   auto input_shape = input->shape();
 
   std::vector<int32_t> output_shape = input_shape;
-  int axis = GetAxis() < 0 ? GetAxis() + input_shape.size() : GetAxis();
+  auto axis = GetAxis() < 0 ? GetAxis() + input_shape.size() : GetAxis();
   if (axis < 0 || axis > input_shape.size()) {
     MS_LOG(ERROR) << "Invalid axis " << GetAxis();
     return RET_PARAM_INVALID;

mindspore/lite/src/ops/strided_slice.cc

@@ -89,7 +89,7 @@ constexpr int kStridedSliceInputNum = 1;
 }  // namespace
 
 void StridedSlice::ApplyNewAxisMask() {
-  for (int i = 0; i < new_axis_mask_.size(); i++) {
+  for (size_t i = 0; i < new_axis_mask_.size(); i++) {
     if (new_axis_mask_.at(i)) {
       ndim_ += 1;
       in_shape_.insert(in_shape_.begin() + i, 1);
@@ -112,7 +112,7 @@ void StridedSlice::ApplyNewAxisMask() {
 std::vector<int> StridedSlice::ApplyShrinkMask(std::vector<int> out_shape) {
   auto old_out_shape = out_shape;
   out_shape.clear();
-  for (int i = 0; i < shrink_axis_mask_.size(); i++) {
+  for (size_t i = 0; i < shrink_axis_mask_.size(); i++) {
     if (shrink_axis_mask_.at(i)) {
       ends_.at(i) = begins_.at(i) + 1;
       strides_.at(i) = 1;
@@ -120,7 +120,7 @@ std::vector<int> StridedSlice::ApplyShrinkMask(std::vector<int> out_shape) {
       out_shape.emplace_back(old_out_shape.at(i));
     }
   }
-  for (int i = shrink_axis_mask_.size(); i < old_out_shape.size(); i++) {
+  for (size_t i = shrink_axis_mask_.size(); i < old_out_shape.size(); i++) {
     out_shape.emplace_back(old_out_shape.at(i));
   }
   return out_shape;
@@ -128,7 +128,7 @@ std::vector<int> StridedSlice::ApplyShrinkMask(std::vector<int> out_shape) {
 
 /*only one bit will be used if multiple bits are true.*/
 void StridedSlice::ApplyEllipsisMask() {
-  for (int i = 0; i < ellipsis_mask_.size(); i++) {
+  for (size_t i = 0; i < ellipsis_mask_.size(); i++) {
     if (ellipsis_mask_.at(i)) {
       begins_.at(i) = 0;
       ends_.at(i) = in_shape_.at(i);
@@ -204,7 +204,7 @@ int StridedSlice::InferShape(std::vector<lite::tensor::Tensor *> inputs, std::ve
 
   output_shape.clear();
   output_shape.resize(in_shape_.size());
-  for (int i = 0; i < in_shape_.size(); i++) {
+  for (int i = 0; i < static_cast<int>(in_shape_.size()); i++) {
     if (i < ndim_ && new_axis_mask_.at(i)) {
       output_shape.at(i) = 1;
     } else {

mindspore/lite/src/ops/transpose.cc

@@ -63,7 +63,7 @@ int Transpose::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<ten
   std::vector<int> in_shape = input->shape();
   std::vector<int> out_shape;
   out_shape.resize(perm.size());
-  for (int i = 0; i < perm.size(); ++i) {
+  for (size_t i = 0; i < perm.size(); ++i) {
     out_shape[i] = in_shape[perm[i]];
   }
   output->set_shape(out_shape);

mindspore/lite/src/ops/unsqueeze.cc

@@ -67,10 +67,10 @@ int Unsqueeze::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<ten
     }
   } else {
     auto sz = in_rank + dim_rank;
-    int in_itr = 0;
+    size_t in_itr = 0;
-    int ax_itr = 0;
+    size_t ax_itr = 0;
-    for (int i = 0; i < sz; i++) {
+    for (size_t i = 0; i < sz; i++) {
-      if (ax_itr < dim_rank && dims[ax_itr] == i) {
+      if (ax_itr < dim_rank && dims[ax_itr] == static_cast<int>(i)) {
         out_shape.emplace_back(1);
         ax_itr++;
       } else if (ax_itr < dim_rank && dims[ax_itr] + sz == i) {

mindspore/lite/src/ops/unstack.cc

@@ -39,7 +39,7 @@ int Unstack::InferShape(std::vector<tensor::Tensor *> inputs, std::vector<tensor
   MS_ASSERT(input != nullptr);
   auto input_shape = input->shape();
 
-  int axis = GetAxis() < 0 ? GetAxis() + input_shape.size() : GetAxis();
+  auto axis = GetAxis() < 0 ? GetAxis() + input_shape.size() : GetAxis();
   if (axis < 0 || axis >= input_shape.size()) {
     MS_LOG(ERROR) << "Invalid axis " << GetAxis();
     return RET_PARAM_INVALID;

mindspore/lite/src/ops/where.cc

@@ -66,8 +66,8 @@ int Where::InferShape(std::vector<tensor::Tensor *> inputs_, std::vector<tensor:
   auto shape_tmp1 = inputs_.at(1)->shape();
   auto shape_tmp2 = inputs_.at(2)->shape();
   int axisout = 0;
-  int temp = 0;
+  size_t temp = 0;
-  for (int j = 0; j < shape_tmp.size(); j++) {
+  for (size_t j = 0; j < shape_tmp.size(); j++) {
     if (shape_tmp[j] == shape_tmp1[j] && shape_tmp[j] != shape_tmp2[j]) {
       axisout = j;
       break;