hs_tohidi
/
cimp-impl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
Browse Source

Fix: Use absolute backbone weights path for C++ tests; add BBRegressor debug tensor saves and logging; sync Python debug saves

resnet
mht 3 weeks ago
parent
02923684ba
commit
b24b8525cc
3 changed files with 137 additions and 14 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 67
      cimp/bb_regressor/bb_regressor.cpp
  2. 52
      ltr/models/bbreg/atom_iou_net.py
  3. 32
      test/test_models.cpp

67
cimp/bb_regressor/bb_regressor.cpp
View File

@ -8,10 +8,13 @@
// Add CUDA includes for required CUDA implementation
#include <cuda_runtime.h>
#include <ATen/cuda/CUDAContext.h>
#include <sys/stat.h>
#include <sys/types.h>
// Use the PrRoIPooling implementation
#include "prroi_pooling_gpu.h"
#include "prroi_pooling_gpu_impl.cuh"
#include "utils.h"
// PrRoIPool2D implementation (requires CUDA)
PrRoIPool2D::PrRoIPool2D(int pooled_height, int pooled_width, float spatial_scale)
@ -507,7 +510,8 @@ void BBRegressor::to(torch::Device device) {
}
// Get IoU features from backbone features
std::vector<torch::Tensor> BBRegressor::get_iou_feat(std::vector<torch::Tensor> feat2_input) {
std::vector<torch::Tensor> BBRegressor::get_iou_feat(std::vector<torch::Tensor> feat2_input, int sample_idx) {
std::cout << "[DEBUG] Entered get_iou_feat with sample_idx=" << sample_idx << std::endl;
torch::Tensor feat3_t_original = feat2_input[0];
torch::Tensor feat4_t_original = feat2_input[1];
@ -527,11 +531,62 @@ std::vector<torch::Tensor> BBRegressor::get_iou_feat(std::vector<torch::Tensor>
torch::NoGradGuard no_grad;
torch::Tensor c3_t_1 = conv3_1t->forward(feat3_t);
torch::Tensor c3_t = conv3_2t->forward(c3_t_1);
torch::Tensor c4_t_1 = conv4_1t->forward(feat4_t);
torch::Tensor c4_t = conv4_2t->forward(c4_t_1);
// Ensure debug directory exists for sample 0
if (sample_idx == 0) {
const char* debug_dir = "test/output/bb_regressor";
struct stat st = {0};
if (stat(debug_dir, &st) == -1) {
mkdir(debug_dir, 0777);
}
}
// conv3_1t
auto c3_1t_conv = conv3_1t[0]->as<torch::nn::Conv2d>()->forward(feat3_t);
auto c3_1t_bn = conv3_1t[1]->as<torch::nn::BatchNorm2d>()->forward(c3_1t_conv);
auto c3_1t_relu = conv3_1t[2]->as<torch::nn::ReLU>()->forward(c3_1t_bn);
if (sample_idx == 0) {
std::cout << "[DEBUG] About to save debug tensors for sample_idx == 0" << std::endl;
save_tensor_to_file(c3_1t_bn.cpu(), "test/output/bb_regressor/sample_0_debug_conv3_1t_bn.pt");
save_tensor_to_file(c3_1t_relu.cpu(), "test/output/bb_regressor/sample_0_debug_conv3_1t_relu.pt");
std::cout << "conv3_1t_bn: dtype=" << c3_1t_bn.dtype() << ", device=" << c3_1t_bn.device() << ", shape=" << c3_1t_bn.sizes() << std::endl;
std::cout << "conv3_1t_relu: dtype=" << c3_1t_relu.dtype() << ", device=" << c3_1t_relu.device() << ", shape=" << c3_1t_relu.sizes() << std::endl;
}
auto c3_t_1 = c3_1t_relu;
// conv3_2t
auto c3_2t_conv = conv3_2t[0]->as<torch::nn::Conv2d>()->forward(c3_t_1);
auto c3_2t_bn = conv3_2t[1]->as<torch::nn::BatchNorm2d>()->forward(c3_2t_conv);
auto c3_2t_relu = conv3_2t[2]->as<torch::nn::ReLU>()->forward(c3_2t_bn);
if (sample_idx == 0) {
std::cout << "[DEBUG] About to save debug tensors for conv3_2t, sample_idx == 0" << std::endl;
save_tensor_to_file(c3_2t_bn.cpu(), "test/output/bb_regressor/sample_0_debug_conv3_2t_bn.pt");
save_tensor_to_file(c3_2t_relu.cpu(), "test/output/bb_regressor/sample_0_debug_conv3_2t_relu.pt");
std::cout << "conv3_2t_bn: dtype=" << c3_2t_bn.dtype() << ", device=" << c3_2t_bn.device() << ", shape=" << c3_2t_bn.sizes() << std::endl;
std::cout << "conv3_2t_relu: dtype=" << c3_2t_relu.dtype() << ", device=" << c3_2t_relu.device() << ", shape=" << c3_2t_relu.sizes() << std::endl;
}
auto c3_t = c3_2t_relu;
// conv4_1t
auto c4_1t_conv = conv4_1t[0]->as<torch::nn::Conv2d>()->forward(feat4_t);
auto c4_1t_bn = conv4_1t[1]->as<torch::nn::BatchNorm2d>()->forward(c4_1t_conv);
auto c4_1t_relu = conv4_1t[2]->as<torch::nn::ReLU>()->forward(c4_1t_bn);
if (sample_idx == 0) {
std::cout << "[DEBUG] About to save debug tensors for conv4_1t, sample_idx == 0" << std::endl;
save_tensor_to_file(c4_1t_bn.cpu(), "test/output/bb_regressor/sample_0_debug_conv4_1t_bn.pt");
save_tensor_to_file(c4_1t_relu.cpu(), "test/output/bb_regressor/sample_0_debug_conv4_1t_relu.pt");
std::cout << "conv4_1t_bn: dtype=" << c4_1t_bn.dtype() << ", device=" << c4_1t_bn.device() << ", shape=" << c4_1t_bn.sizes() << std::endl;
std::cout << "conv4_1t_relu: dtype=" << c4_1t_relu.dtype() << ", device=" << c4_1t_relu.device() << ", shape=" << c4_1t_relu.sizes() << std::endl;
}
auto c4_t_1 = c4_1t_relu;
// conv4_2t
auto c4_2t_conv = conv4_2t[0]->as<torch::nn::Conv2d>()->forward(c4_t_1);
auto c4_2t_bn = conv4_2t[1]->as<torch::nn::BatchNorm2d>()->forward(c4_2t_conv);
auto c4_2t_relu = conv4_2t[2]->as<torch::nn::ReLU>()->forward(c4_2t_bn);
if (sample_idx == 0) {
std::cout << "[DEBUG] About to save debug tensors for conv4_2t, sample_idx == 0" << std::endl;
save_tensor_to_file(c4_2t_bn.cpu(), "test/output/bb_regressor/sample_0_debug_conv4_2t_bn.pt");
save_tensor_to_file(c4_2t_relu.cpu(), "test/output/bb_regressor/sample_0_debug_conv4_2t_relu.pt");
std::cout << "conv4_2t_bn: dtype=" << c4_2t_bn.dtype() << ", device=" << c4_2t_bn.device() << ", shape=" << c4_2t_bn.sizes() << std::endl;
std::cout << "conv4_2t_relu: dtype=" << c4_2t_relu.dtype() << ", device=" << c4_2t_relu.device() << ", shape=" << c4_2t_relu.sizes() << std::endl;
}
auto c4_t = c4_2t_relu;
return {c3_t.contiguous(), c4_t.contiguous()}; // Ensure output is contiguous and float32
}

52
ltr/models/bbreg/atom_iou_net.py
View File

@ -2,6 +2,7 @@ import torch.nn as nn
import torch
from ltr.models.layers.blocks import LinearBlock
from ltr.external.PreciseRoIPooling.pytorch.prroi_pool import PrRoIPool2D
import os
torch.cuda.empty_cache()
@ -143,11 +144,50 @@ class AtomIoUNet(nn.Module):
return fc34_3_r, fc34_4_r
def get_iou_feat(self, feat2):
"""Get IoU prediction features from a 4 or 5 dimensional backbone input."""
def get_iou_feat(self, feat2, sample_idx=None):
feat2 = [f.reshape(-1, *f.shape[-3:]) if f.dim()==5 else f for f in feat2]
feat3_t, feat4_t = feat2
c3_t = self.conv3_2t(self.conv3_1t(feat3_t))
c4_t = self.conv4_2t(self.conv4_1t(feat4_t))
return c3_t, c4_t
debug_dir = 'test/output_py/bb_regressor/'
if sample_idx == 0:
os.makedirs(debug_dir, exist_ok=True)
# conv3_1t
c3_1t_conv = self.conv3_1t[0](feat3_t)
c3_1t_bn = self.conv3_1t[1](c3_1t_conv)
c3_1t_relu = self.conv3_1t[2](c3_1t_bn)
if sample_idx == 0:
torch.save(c3_1t_bn.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv3_1t_bn_py.pt'))
torch.save(c3_1t_relu.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv3_1t_relu_py.pt'))
print(f"conv3_1t_bn: dtype={c3_1t_bn.dtype}, device={c3_1t_bn.device}, shape={tuple(c3_1t_bn.shape)}")
print(f"conv3_1t_relu: dtype={c3_1t_relu.dtype}, device={c3_1t_relu.device}, shape={tuple(c3_1t_relu.shape)}")
c3_t_1 = c3_1t_relu
# conv3_2t
c3_2t_conv = self.conv3_2t[0](c3_t_1)
c3_2t_bn = self.conv3_2t[1](c3_2t_conv)
c3_2t_relu = self.conv3_2t[2](c3_2t_bn)
if sample_idx == 0:
torch.save(c3_2t_bn.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv3_2t_bn_py.pt'))
torch.save(c3_2t_relu.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv3_2t_relu_py.pt'))
print(f"conv3_2t_bn: dtype={c3_2t_bn.dtype}, device={c3_2t_bn.device}, shape={tuple(c3_2t_bn.shape)}")
print(f"conv3_2t_relu: dtype={c3_2t_relu.dtype}, device={c3_2t_relu.device}, shape={tuple(c3_2t_relu.shape)}")
c3_t = c3_2t_relu
# conv4_1t
c4_1t_conv = self.conv4_1t[0](feat4_t)
c4_1t_bn = self.conv4_1t[1](c4_1t_conv)
c4_1t_relu = self.conv4_1t[2](c4_1t_bn)
if sample_idx == 0:
torch.save(c4_1t_bn.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv4_1t_bn_py.pt'))
torch.save(c4_1t_relu.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv4_1t_relu_py.pt'))
print(f"conv4_1t_bn: dtype={c4_1t_bn.dtype}, device={c4_1t_bn.device}, shape={tuple(c4_1t_bn.shape)}")
print(f"conv4_1t_relu: dtype={c4_1t_relu.dtype}, device={c4_1t_relu.device}, shape={tuple(c4_1t_relu.shape)}")
c4_t_1 = c4_1t_relu
# conv4_2t
c4_2t_conv = self.conv4_2t[0](c4_t_1)
c4_2t_bn = self.conv4_2t[1](c4_2t_conv)
c4_2t_relu = self.conv4_2t[2](c4_2t_bn)
if sample_idx == 0:
torch.save(c4_2t_bn.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv4_2t_bn_py.pt'))
torch.save(c4_2t_relu.cpu(), os.path.join(debug_dir, 'sample_0_debug_conv4_2t_relu_py.pt'))
print(f"conv4_2t_bn: dtype={c4_2t_bn.dtype}, device={c4_2t_bn.device}, shape={tuple(c4_2t_bn.shape)}")
print(f"conv4_2t_relu: dtype={c4_2t_relu.dtype}, device={c4_2t_relu.device}, shape={tuple(c4_2t_relu.shape)}")
c4_t = c4_2t_relu
return [c3_t, c4_t]

32
test/test_models.cpp
View File

@ -9,11 +9,14 @@
#include <ATen/Context.h> // Required for globalContext
// #include <opencv2/opencv.hpp> // REMOVED
#include <algorithm> // For std::find
#include <unistd.h> // For getcwd
#include <sys/stat.h> // For stat
// Project headers
#include "../cimp/resnet/resnet.h"
#include "../cimp/classifier/classifier.h"
#include "../cimp/bb_regressor/bb_regressor.h"
#include "../cimp/bb_regressor/utils.h"
namespace fs = std::filesystem;
@ -112,6 +115,13 @@ void save_tensor_as_jit_module(const torch::Tensor& tensor, const std::string& f
}
int main(int argc, char* argv[]) {
// Print current working directory
char cwd[1024];
if (getcwd(cwd, sizeof(cwd)) != NULL) {
std::cout << "[DEBUG] Current working directory: " << cwd << std::endl;
} else {
std::cerr << "[DEBUG] Error getting current working directory." << std::endl;
}
if (argc < 4) {
// Original usage message for consistency with how run_tests.sh calls it
std::cerr << "Usage: " << argv[0] << " <base_input_dir_path> <base_output_dir_path> <num_samples> [model_to_test]" << std::endl;
@ -160,7 +170,9 @@ int main(int argc, char* argv[]) {
// --- Initialize Models (once) ---
std::cout << "--- Initializing Models ---" << std::endl;
std::string resnet_weights_path = "exported_weights/backbone_regenerated";
// Set ResNet weights path to absolute directory as per user instruction
std::string resnet_weights_path = "/media/mht/ADATA/repos/cpp_tracker/backbone_pure_tensors/";
std::cout << "[DEBUG] Using absolute ResNet weights path: " << resnet_weights_path << std::endl;
std::string bb_reg_weights_path = "exported_weights/bb_regressor";
std::string classifier_weights_path = "exported_weights/classifier";
std::optional<cimp::resnet::ResNet> resnet_model_opt;
@ -169,6 +181,22 @@ int main(int argc, char* argv[]) {
std::optional<BBRegressor> bb_regressor_model_opt_wrapped;
bool models_initialized_ok = true;
std::cout << "ResNet weights path: " << resnet_weights_path << std::endl;
struct stat st_resnet = {0};
if (stat(resnet_weights_path.c_str(), &st_resnet) != 0 || !S_ISDIR(st_resnet.st_mode)) {
std::cerr << "[ERROR] ResNet weights directory does not exist: " << resnet_weights_path << std::endl;
}
std::cout << "BBRegressor weights path: " << bb_reg_weights_path << std::endl;
struct stat st_bbreg = {0};
if (stat(bb_reg_weights_path.c_str(), &st_bbreg) != 0 || !S_ISDIR(st_bbreg.st_mode)) {
std::cerr << "[ERROR] BBRegressor weights directory does not exist: " << bb_reg_weights_path << std::endl;
}
std::cout << "Classifier weights path: " << classifier_weights_path << std::endl;
struct stat st_clf = {0};
if (stat(classifier_weights_path.c_str(), &st_clf) != 0 || !S_ISDIR(st_clf.st_mode)) {
std::cerr << "[ERROR] Classifier weights directory does not exist: " << classifier_weights_path << std::endl;
}
try {
std::vector<std::string> output_layers_resnet = {
"conv1_output", "bn1_output", "relu1_output", "maxpool_output",
@ -342,7 +370,7 @@ int main(int argc, char* argv[]) {
resnet_outputs["layer3"].clone()
};
std::vector<torch::Tensor> iou_feats = (*bb_regressor_model_opt_wrapped).get_iou_feat(backbone_feats_for_bb);
std::vector<torch::Tensor> iou_feats = (*bb_regressor_model_opt_wrapped).get_iou_feat(backbone_feats_for_bb, i);
if (iou_feats.size() >= 1) save_tensor_to_file(iou_feats[0], (bb_reg_out_dir / (sample_suffix + "_iou_feat0.pt")).string());
if (iou_feats.size() >= 2) save_tensor_to_file(iou_feats[1], (bb_reg_out_dir / (sample_suffix + "_iou_feat1.pt")).string());

Write Preview
Loading…
Cancel
Save