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

Fix BBRegressor: Apply modulation before PrRoIPool in predict_iou

resnet
mht 2 months ago
parent
e61886fb23
commit
8ed90f273e
1 changed files with 73 additions and 53 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. 126
      cimp/bb_regressor/bb_regressor.cpp

126
cimp/bb_regressor/bb_regressor.cpp
View File

@ -647,19 +647,56 @@ torch::Tensor BBRegressor::predict_iou(std::vector<torch::Tensor> modulation,
auto feat_device = feat[0].device();
roi = roi.to(feat_device);
// Apply ROI pooling to get features for each proposal
auto pooled_feat1 = prroi_pool3t->forward(feat[0], roi); // Output: [batch_size * num_proposals, C, 5, 5]
auto pooled_feat2 = prroi_pool4t->forward(feat[1], roi); // Output: [batch_size * num_proposals, C, 3, 3]
// Apply modulation vectors BEFORE PrRoIPooling
auto mod0_4d = modulation[0].to(feat_device);
auto mod1_4d = modulation[1].to(feat_device);
if (mod0_4d.dim() == 2) {
mod0_4d = mod0_4d.reshape({mod0_4d.size(0), mod0_4d.size(1), 1, 1});
}
if (mod1_4d.dim() == 2) {
mod1_4d = mod1_4d.reshape({mod1_4d.size(0), mod1_4d.size(1), 1, 1});
}
std::cout << " Pooled shapes:" << std::endl;
std::cout << " pooled_feat1 (from prroi_pool3t on feat[0]): [" << pooled_feat1.sizes() << "] dev: " << pooled_feat1.device() << std::endl;
std::cout << " pooled_feat2 (from prroi_pool4t on feat[1]): [" << pooled_feat2.sizes() << "] dev: " << pooled_feat2.device() << std::endl;
// Ensure modulation vectors are broadcastable with features
// Features (feat[0], feat[1]) are [batch_size, channels, H, W]
// Modulation (mod0_4d, mod1_4d) should be [batch_size, channels, 1, 1]
// If num_proposals > 1, the pooling happens on features that are effectively repeated.
// The modulation is per-image, not per-proposal before pooling.
torch::Tensor modulated_feat0 = feat[0] * mod0_4d;
torch::Tensor modulated_feat1 = feat[1] * mod1_4d;
// Apply ROI pooling to get features for each proposal from MODULATED features
auto pooled_feat1 = prroi_pool3t->forward(modulated_feat0, roi); // Output: [batch_size * num_proposals, C, 5, 5]
auto pooled_feat2 = prroi_pool4t->forward(modulated_feat1, roi);
std::cout << " Modulated and Pooled shapes:" << std::endl;
std::cout << " pooled_feat1 (from prroi_pool3t on modulated_feat0): [" << pooled_feat1.sizes() << "] dev: " << pooled_feat1.device() << std::endl;
std::cout << " pooled_feat2 (from prroi_pool4t on modulated_feat1): [" << pooled_feat2.sizes() << "] dev: " << pooled_feat2.device() << std::endl;
std::cout << " IoU predictor dimensions:" << std::endl;
std::cout << " weight: [" << iou_predictor->weight.sizes() << "]" << std::endl;
std::cout << " bias: [" << iou_predictor->bias.sizes() << "]" << std::endl;
try {
// The feat_prod_0 and feat_prod_1 are now directly the pooled_feat1 and pooled_feat2
// as modulation was applied before pooling.
auto x0 = fc3_rt.forward(pooled_feat1);
auto x1 = fc4_rt.forward(pooled_feat2);
auto ioufeat_final = torch::cat({x0, x1}, 1).contiguous();
// Ensure iou_predictor is on the correct device
iou_predictor->to(target_device);
auto iou_scores = iou_predictor->forward(ioufeat_final);
// Ensure iou_scores is on the correct device before returning
iou_scores = iou_scores.to(target_device);
// The following block for feat_prod_0 and feat_prod_1 is no longer needed as modulation is done pre-pool.
/*
auto mod0_4d = modulation[0].to(target_device);
auto mod1_4d = modulation[1].to(target_device);
@ -682,59 +719,42 @@ torch::Tensor BBRegressor::predict_iou(std::vector<torch::Tensor> modulation,
std::cout << " mod1_4d: [" << mod1_4d.sizes() << "] dev: " << mod1_4d.device() << std::endl;
auto feat_prod_0 = pooled_feat1 * mod0_4d;
auto feat_prod_1 = pooled_feat2 * mod1_4d;
std::cout << " After element-wise product with modulation:\n feat_prod_0 (pooled_feat1 * mod0_4d): [" << feat_prod_0.sizes() << "] dev: " << feat_prod_0.device() << "\n feat_prod_1 (pooled_feat2 * mod1_4d): [" << feat_prod_1.sizes() << "] dev: " << feat_prod_1.device() << std::endl;
std::cout << " Applying fc3_rt to feat_prod_0..." << std::endl;
auto x0 = fc3_rt.forward(feat_prod_0); // Corrected: . instead of ->
std::cout << " Applying fc4_rt to feat_prod_1..." << std::endl;
auto x1 = fc4_rt.forward(feat_prod_1); // Corrected: . instead of ->
std::cout << " After fc_rt blocks:\n x0 (fc3_rt output): [" << x0.sizes() << "] dev: " << x0.device() << "\n x1 (fc4_rt output): [" << x1.sizes() << "] dev: " << x1.device() << std::endl;
auto feat_prod_1 = pooled_feat2 * mod1_4d;
auto ioufeat_final = torch::cat(std::vector<torch::Tensor>{x0, x1}, 1).contiguous(); // Corrected: std::vector wrapper
std::cout << " Concatenated ioufeat_final: [" << ioufeat_final.sizes() << "] dev: " << ioufeat_final.device() << std::endl;
std::cout << " Feature product shapes (pooled_feat * mod_vec):" << std::endl;
std::cout << " feat_prod_0: [" << feat_prod_0.sizes() << "] dev: " << feat_prod_0.device() << std::endl;
std::cout << " feat_prod_1: [" << feat_prod_1.sizes() << "] dev: " << feat_prod_1.device() << std::endl;
// Forward through linear blocks
// Ensure fc3_rt and fc4_rt are on the correct device
fc3_rt.to(target_device);
fc4_rt.to(target_device);
torch::Tensor iou_scores;
try {
std::cout << " Applying final iou_predictor on GPU" << std::endl;
iou_predictor->to(target_device);
iou_scores = iou_predictor->forward(ioufeat_final.to(target_device));
std::cout << " Final iou_predictor on GPU successful. Output scores shape: [" << iou_scores.sizes() << "]" << std::endl;
} catch (const std::exception& cuda_error) {
std::cout << " GPU iou_predictor->forward() failed: " << cuda_error.what() << std::endl;
std::cout << " Falling back to CPU for final iou_predictor" << std::endl;
auto ioufeat_final_cpu = ioufeat_final.to(torch::kCPU).contiguous();
auto weight_cpu = iou_predictor->weight.to(torch::kCPU).contiguous();
auto bias_cpu = torch::Tensor();
if (iou_predictor->bias.defined()) {
bias_cpu = iou_predictor->bias.to(torch::kCPU).contiguous();
}
auto x0 = fc3_rt.forward(feat_prod_0);
auto x1 = fc4_rt.forward(feat_prod_1);
std::cout << " fc_rt output shapes:" << std::endl;
std::cout << " x0 (fc3_rt output): [" << x0.sizes() << "] dev: " << x0.device() << std::endl;
std::cout << " x1 (fc4_rt output): [" << x1.sizes() << "] dev: " << x1.device() << std::endl;
std::cout << " DEBUG CPU Fallback: ioufeat_final_cpu device: " << ioufeat_final_cpu.device() << std::endl;
std::cout << " DEBUG CPU Fallback: weight_cpu device: " << weight_cpu.device() << std::endl;
if (bias_cpu.defined()) {
std::cout << " DEBUG CPU Fallback: bias_cpu device: " << bias_cpu.device() << std::endl;
} else {
std::cout << " DEBUG CPU Fallback: bias_cpu is undefined." << std::endl;
}
try {
iou_scores = torch::nn::functional::linear(ioufeat_final_cpu, weight_cpu, bias_cpu);
std::cout << " CPU fallback torch::nn::functional::linear() successful. Output device: " << iou_scores.device() << std::endl;
} catch (const std::exception& cpu_fwd_error) {
std::cerr << "ERROR during CPU torch::nn::functional::linear(): " << cpu_fwd_error.what() << std::endl;
iou_predictor->to(target_device);
throw;
}
iou_predictor->to(target_device);
auto ioufeat_final = torch::cat({x0, x1}, 1).contiguous();
std::cout << " ioufeat_final shape: [" << ioufeat_final.sizes() << "] dev: " << ioufeat_final.device() << std::endl;
// Ensure iou_predictor is on the correct device
iou_predictor->to(target_device);
auto iou_scores = iou_predictor->forward(ioufeat_final);
// Ensure iou_scores is on the correct device before returning
iou_scores = iou_scores.to(target_device);
*/
// Ensure iou_scores is on the correct device before returning.
// This was already done above, but as a final check:
if (iou_scores.device() != target_device) {
iou_scores = iou_scores.to(target_device);
}
std::cout << " iou_scores raw shape: [" << iou_scores.size(0) << ", " << iou_scores.size(1) << "]" << std::endl;
iou_scores = iou_scores.reshape({batch_size, num_proposals});
std::cout << " Final iou_scores shape: [" << iou_scores.size(0) << ", " << iou_scores.size(1) << "]" << std::endl;

Write Preview
Loading…
Cancel
Save